{
 "generated": "2026-09-08",
 "runs": [
  {
   "suite": "PARTIAL-KILLED-nullschema",
   "model": "qwen38-vendor-qwen-think",
   "profile": "vendor-qwen-think",
   "n": 16,
   "passed": 9,
   "accuracy": 56.2,
   "ci": [
    33.2,
    76.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "VOID-degenerate-nullschema",
   "model": "granite-4.2-30b-mlx-q4",
   "profile": "extraction",
   "n": 72,
   "passed": 72,
   "accuracy": 100.0,
   "ci": [
    94.9,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "VOID-degenerate-nullschema",
   "model": "reap-60b-gguf-q4km",
   "profile": "extraction",
   "n": 72,
   "passed": 72,
   "accuracy": 100.0,
   "ci": [
    94.9,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "chainwalk",
   "model": "bonsai-27b-1bit",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "mlx",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "bonsai-8b-1bit",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "btl-4-q4km",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "btl-4",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "flashnext-4.27bpw-m64",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-12b-r1",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-12b-r2",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-12b-r3",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-12b",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "48abd22e0117fdda"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e2b-r1",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e2b-r2",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e2b-r3",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e2b",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "48abd22e0117fdda"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e4b-r1",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e4b-r2",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e4b-r3",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "gemma4-e4b",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "48abd22e0117fdda"
  },
  {
   "suite": "chainwalk",
   "model": "k2-36b-ctx128k-q8",
   "profile": "extraction",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "k2-36b-ctx32k",
   "profile": "extraction",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "k2-horizon-3.7b",
   "profile": "extraction",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "qwen-agentworld-35b",
   "profile": "extraction",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "qwen3-next-80b-ag",
   "profile": "extraction",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "qwen3-next-80b-reap-ag",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "qwen3.6-35b-ag",
   "profile": "extraction",
   "n": 2,
   "passed": 1,
   "accuracy": 50.0,
   "ci": [
    9.5,
    90.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "qwen3.8-9b-distill",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "chainwalk",
   "model": "qwen3.8-iq1s",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "d31d3c4c6285617f"
  },
  {
   "suite": "chainwalk",
   "model": "ternary-bonsai-27b",
   "profile": "agentic-fast",
   "n": 2,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    65.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "129a9e74408c89194f3cbffeb9c21a39c3ed006a1cccbc77cb5f177bc5bc55b6",
   "grader_id": "f4bfcf6f040b0978"
  },
  {
   "suite": "contract",
   "model": "qwen3-next-80b-reap-mlx-mixed36",
   "profile": "extraction",
   "n": 48,
   "passed": 26,
   "accuracy": 54.2,
   "ci": [
    40.3,
    67.4
   ],
   "runtime": "mlx",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "486601ba23034dd6"
  },
  {
   "suite": "contract",
   "model": "qwen3-next-80b-reap-mlx-q4",
   "profile": "extraction",
   "n": 36,
   "passed": 17,
   "accuracy": 47.2,
   "ci": [
    32.0,
    63.0
   ],
   "runtime": "mlx",
   "dataset_id": "ab4bb33923bd0ed693809cf204fde22ef379a21a3be689402388aebf0d38caed",
   "grader_id": "2dd146852463f032"
  },
  {
   "suite": "contract",
   "model": "qwen3.8-27b-mlx-4bit",
   "profile": "extraction",
   "n": 48,
   "passed": 36,
   "accuracy": 75.0,
   "ci": [
    61.2,
    85.1
   ],
   "runtime": "mlx",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "486601ba23034dd6"
  },
  {
   "suite": "contract",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 48,
   "passed": 12,
   "accuracy": 25.0,
   "ci": [
    14.9,
    38.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 48,
   "passed": 36,
   "accuracy": 75.0,
   "ci": [
    61.2,
    85.1
   ],
   "runtime": "mlx",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 48,
   "passed": 36,
   "accuracy": 75.0,
   "ci": [
    61.2,
    85.1
   ],
   "runtime": "mlx",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 48,
   "passed": 10,
   "accuracy": 20.8,
   "ci": [
    11.7,
    34.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 48,
   "passed": 34,
   "accuracy": 70.8,
   "ci": [
    56.8,
    81.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "btl-4",
   "profile": "extraction",
   "n": 48,
   "passed": 31,
   "accuracy": 64.6,
   "ci": [
    50.4,
    76.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "flashnext-4.27bpw-m64",
   "profile": "extraction",
   "n": 48,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    7.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "486601ba23034dd6"
  },
  {
   "suite": "contract",
   "model": "gemma4-12b",
   "profile": "extraction",
   "n": 36,
   "passed": 24,
   "accuracy": 66.7,
   "ci": [
    50.3,
    79.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "ab4bb33923bd0ed693809cf204fde22ef379a21a3be689402388aebf0d38caed",
   "grader_id": "2dd146852463f032"
  },
  {
   "suite": "contract",
   "model": "granite-4.2-30b",
   "profile": "extraction",
   "n": 36,
   "passed": 24,
   "accuracy": 66.7,
   "ci": [
    50.3,
    79.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "ab4bb33923bd0ed693809cf204fde22ef379a21a3be689402388aebf0d38caed",
   "grader_id": "2dd146852463f032"
  },
  {
   "suite": "contract",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 48,
   "passed": 11,
   "accuracy": 22.9,
   "ci": [
    13.3,
    36.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 48,
   "passed": 34,
   "accuracy": 70.8,
   "ci": [
    56.8,
    81.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "mlx-community-Qwen3.6-35B-A3B-4bit",
   "profile": "extraction",
   "n": 48,
   "passed": 13,
   "accuracy": 27.1,
   "ci": [
    16.6,
    41.0
   ],
   "runtime": "mlx",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "486601ba23034dd6"
  },
  {
   "suite": "contract",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 48,
   "passed": 33,
   "accuracy": 68.8,
   "ci": [
    54.7,
    80.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "ornith-35b-a3b-q40",
   "profile": "extraction",
   "n": 48,
   "passed": 32,
   "accuracy": 66.7,
   "ci": [
    52.5,
    78.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "q36-toolparser",
   "profile": "extraction",
   "n": 48,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    7.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "486601ba23034dd6"
  },
  {
   "suite": "contract",
   "model": "qwen3-next-80b-reap",
   "profile": "extraction",
   "n": 48,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    7.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "486601ba23034dd6"
  },
  {
   "suite": "contract",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 48,
   "passed": 12,
   "accuracy": 25.0,
   "ci": [
    14.9,
    38.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "reapmix36-rapid-mlx",
   "profile": "extraction",
   "n": 36,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    9.6
   ],
   "runtime": "mlx",
   "dataset_id": "ab4bb33923bd0ed693809cf204fde22ef379a21a3be689402388aebf0d38caed",
   "grader_id": "2dd146852463f032"
  },
  {
   "suite": "contract",
   "model": "reapq4-mlx_lm",
   "profile": "extraction",
   "n": 36,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    9.6
   ],
   "runtime": "mlx",
   "dataset_id": "ab4bb33923bd0ed693809cf204fde22ef379a21a3be689402388aebf0d38caed",
   "grader_id": "2dd146852463f032"
  },
  {
   "suite": "contract",
   "model": "reapq4-rapid-mlx",
   "profile": "extraction",
   "n": 36,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    9.6
   ],
   "runtime": "mlx",
   "dataset_id": "ab4bb33923bd0ed693809cf204fde22ef379a21a3be689402388aebf0d38caed",
   "grader_id": "2dd146852463f032"
  },
  {
   "suite": "contract",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 48,
   "passed": 36,
   "accuracy": 75.0,
   "ci": [
    61.2,
    85.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "contract",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 48,
   "passed": 11,
   "accuracy": 22.9,
   "ci": [
    13.3,
    36.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "1fe53d30cb5480f6844365a851a35bf098f7b53e5e537f8876639a68651a8eb0",
   "grader_id": "cc2d23c5bae45474"
  },
  {
   "suite": "enrichment",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 54,
   "passed": 43,
   "accuracy": 79.6,
   "ci": [
    67.1,
    88.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 54,
   "passed": 39,
   "accuracy": 72.2,
   "ci": [
    59.1,
    82.4
   ],
   "runtime": "mlx",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 54,
   "passed": 39,
   "accuracy": 72.2,
   "ci": [
    59.1,
    82.4
   ],
   "runtime": "mlx",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 54,
   "passed": 33,
   "accuracy": 61.1,
   "ci": [
    47.8,
    73.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 54,
   "passed": 44,
   "accuracy": 81.5,
   "ci": [
    69.2,
    89.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "btl-4",
   "profile": "extraction",
   "n": 54,
   "passed": 47,
   "accuracy": 87.0,
   "ci": [
    75.6,
    93.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 54,
   "passed": 42,
   "accuracy": 77.8,
   "ci": [
    65.1,
    86.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "gemma4-12b",
   "profile": "study-nothink",
   "n": 54,
   "passed": 42,
   "accuracy": 77.8,
   "ci": [
    65.1,
    86.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "7d661b93852b5ffd"
  },
  {
   "suite": "enrichment",
   "model": "gemma4-e2b",
   "profile": "study-nothink",
   "n": 54,
   "passed": 41,
   "accuracy": 75.9,
   "ci": [
    63.1,
    85.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "7d661b93852b5ffd"
  },
  {
   "suite": "enrichment",
   "model": "gemma4-e4b",
   "profile": "study-nothink",
   "n": 54,
   "passed": 38,
   "accuracy": 70.4,
   "ci": [
    57.2,
    80.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "7d661b93852b5ffd"
  },
  {
   "suite": "enrichment",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 54,
   "passed": 32,
   "accuracy": 59.3,
   "ci": [
    46.0,
    71.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "minicpm5-2b-q8-np1",
   "profile": "extraction",
   "n": 54,
   "passed": 31,
   "accuracy": 57.4,
   "ci": [
    44.2,
    69.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 54,
   "passed": 32,
   "accuracy": 59.3,
   "ci": [
    46.0,
    71.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 54,
   "passed": 43,
   "accuracy": 79.6,
   "ci": [
    67.1,
    88.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "qwen3.8-iq1s",
   "profile": "study-nothink",
   "n": 54,
   "passed": 26,
   "accuracy": 48.1,
   "ci": [
    35.4,
    61.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "7d661b93852b5ffd"
  },
  {
   "suite": "enrichment",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 54,
   "passed": 39,
   "accuracy": 72.2,
   "ci": [
    59.1,
    82.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "enrichment",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 54,
   "passed": 38,
   "accuracy": 70.4,
   "ci": [
    57.2,
    80.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "75361864baa727abe654f0e0f5496d69771dfbe5f6480a3e9e80d2459189f75f",
   "grader_id": "b51222c2ca38cfdf"
  },
  {
   "suite": "epistemics",
   "model": "agents-a1-35b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "2a2f7e4e90d6dd63"
  },
  {
   "suite": "epistemics",
   "model": "bonsai-27b-1bit",
   "profile": "study-nothink",
   "n": 48,
   "passed": 42,
   "accuracy": 87.5,
   "ci": [
    75.3,
    94.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "study-nothink",
   "n": 48,
   "passed": 43,
   "accuracy": 89.6,
   "ci": [
    77.8,
    95.5
   ],
   "runtime": "mlx",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "study-nothink",
   "n": 48,
   "passed": 43,
   "accuracy": 89.6,
   "ci": [
    77.8,
    95.5
   ],
   "runtime": "mlx",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "bonsai-8b-1bit",
   "profile": "study-nothink",
   "n": 48,
   "passed": 38,
   "accuracy": 79.2,
   "ci": [
    65.7,
    88.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "bonsai2-27b-pq2",
   "profile": "study-nothink",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "bonsai2-27b-ptq1",
   "profile": "study-nothink",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "btl-4-q4km",
   "profile": "study-nothink",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "btl-4",
   "profile": "study-nothink",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "edge0-35b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 47,
   "accuracy": 97.9,
   "ci": [
    89.1,
    99.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "gemma4-12b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "2a2f7e4e90d6dd63"
  },
  {
   "suite": "epistemics",
   "model": "gemma4-e2b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 33,
   "accuracy": 68.8,
   "ci": [
    54.7,
    80.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "2a2f7e4e90d6dd63"
  },
  {
   "suite": "epistemics",
   "model": "gemma4-e4b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 47,
   "accuracy": 97.9,
   "ci": [
    89.1,
    99.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "2a2f7e4e90d6dd63"
  },
  {
   "suite": "epistemics",
   "model": "glm-4.7-flash-q40",
   "profile": "extraction",
   "n": 48,
   "passed": 36,
   "accuracy": 75.0,
   "ci": [
    61.2,
    85.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "minicpm5-2b-exl3",
   "profile": "study-nothink",
   "n": 48,
   "passed": 39,
   "accuracy": 81.2,
   "ci": [
    68.1,
    89.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "minicpm5-2b-q8-np1",
   "profile": "study-nothink",
   "n": 48,
   "passed": 38,
   "accuracy": 79.2,
   "ci": [
    65.7,
    88.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "minicpm5-2b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 37,
   "accuracy": 77.1,
   "ci": [
    63.5,
    86.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "neohorse-1-4b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 36,
   "accuracy": 75.0,
   "ci": [
    61.2,
    85.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "qwen3.5-4b-base",
   "profile": "study-nothink",
   "n": 48,
   "passed": 41,
   "accuracy": 85.4,
   "ci": [
    72.8,
    92.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "qwen3.8-27b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 48,
   "accuracy": 100.0,
   "ci": [
    92.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "2a2f7e4e90d6dd63"
  },
  {
   "suite": "epistemics",
   "model": "qwen3.8-9b-distill",
   "profile": "study-nothink",
   "n": 48,
   "passed": 43,
   "accuracy": 89.6,
   "ci": [
    77.8,
    95.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "qwen3.8-iq1s",
   "profile": "study-nothink",
   "n": 48,
   "passed": 27,
   "accuracy": 56.2,
   "ci": [
    42.3,
    69.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "2a2f7e4e90d6dd63"
  },
  {
   "suite": "epistemics",
   "model": "ternary-bonsai-27b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 41,
   "accuracy": 85.4,
   "ci": [
    72.8,
    92.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "epistemics",
   "model": "ternary-bonsai-8b",
   "profile": "study-nothink",
   "n": 48,
   "passed": 35,
   "accuracy": 72.9,
   "ci": [
    59.0,
    83.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "4bce453fd376553c768cca67db1d27f08893309a1270c3f1e66738747ac18f32",
   "grader_id": "acf84972a0ad5f38"
  },
  {
   "suite": "grounding",
   "model": "glm-4.7-flash-mlx-q4",
   "profile": "extraction",
   "n": 125,
   "passed": 67,
   "accuracy": 53.6,
   "ci": [
    44.9,
    62.1
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "glm-4.7-flash-mlx-q8",
   "profile": "extraction",
   "n": 125,
   "passed": 96,
   "accuracy": 76.8,
   "ci": [
    68.7,
    83.3
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "granite-4.2-30b-mlx-q4",
   "profile": "extraction",
   "n": 125,
   "passed": 108,
   "accuracy": 86.4,
   "ci": [
    79.3,
    91.3
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "nemotron-lightning-30b-mlx-4bit",
   "profile": "extraction",
   "n": 125,
   "passed": 71,
   "accuracy": 56.8,
   "ci": [
    48.0,
    65.2
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "ornith-1.5-35b-mlx-4bit",
   "profile": "extraction",
   "n": 125,
   "passed": 84,
   "accuracy": 67.2,
   "ci": [
    58.6,
    74.8
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-8b-mlx-8bit",
   "profile": "extraction",
   "n": 125,
   "passed": 93,
   "accuracy": 74.4,
   "ci": [
    66.1,
    81.2
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b-mlx-4bit",
   "profile": "extraction",
   "n": 125,
   "passed": 109,
   "accuracy": 87.2,
   "ci": [
    80.2,
    92.0
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.8-27b-mlx-4bit",
   "profile": "extraction",
   "n": 125,
   "passed": 115,
   "accuracy": 92.0,
   "ci": [
    85.9,
    95.6
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "agents-a1-35b-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 89,
   "accuracy": 71.2,
   "ci": [
    62.7,
    78.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "agents-a1-35b",
   "profile": "extraction",
   "n": 125,
   "passed": 89,
   "accuracy": 71.2,
   "ci": [
    62.7,
    78.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 125,
   "passed": 84,
   "accuracy": 67.2,
   "ci": [
    58.6,
    74.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 125,
   "passed": 89,
   "accuracy": 71.2,
   "ci": [
    62.7,
    78.4
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 125,
   "passed": 89,
   "accuracy": 71.2,
   "ci": [
    62.7,
    78.4
   ],
   "runtime": "mlx",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 125,
   "passed": 69,
   "accuracy": 55.2,
   "ci": [
    46.5,
    63.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "bonsai2-27b-pq2",
   "profile": "extraction",
   "n": 125,
   "passed": 83,
   "accuracy": 66.4,
   "ci": [
    57.7,
    74.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "bonsai2-27b-ptq1",
   "profile": "extraction",
   "n": 125,
   "passed": 83,
   "accuracy": 66.4,
   "ci": [
    57.7,
    74.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 125,
   "passed": 96,
   "accuracy": 76.8,
   "ci": [
    68.7,
    83.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "btl-4",
   "profile": "extraction",
   "n": 125,
   "passed": 96,
   "accuracy": 76.8,
   "ci": [
    68.7,
    83.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "devstral-small-2-24b-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 99,
   "accuracy": 79.2,
   "ci": [
    71.3,
    85.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 125,
   "passed": 112,
   "accuracy": 89.6,
   "ci": [
    83.0,
    93.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "flashnext-4.27bpw-m64",
   "profile": "extraction",
   "n": 125,
   "passed": 102,
   "accuracy": 81.6,
   "ci": [
    73.9,
    87.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "gemma4-12b-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 105,
   "accuracy": 84.0,
   "ci": [
    76.6,
    89.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "gemma4-12b",
   "profile": "extraction",
   "n": 125,
   "passed": 105,
   "accuracy": 84.0,
   "ci": [
    76.6,
    89.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "gemma4-e2b-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 77,
   "accuracy": 61.6,
   "ci": [
    52.8,
    69.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "gemma4-e2b",
   "profile": "extraction",
   "n": 125,
   "passed": 77,
   "accuracy": 61.6,
   "ci": [
    52.8,
    69.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "gemma4-e4b-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 78,
   "accuracy": 62.4,
   "ci": [
    53.7,
    70.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "gemma4-e4b",
   "profile": "extraction",
   "n": 125,
   "passed": 78,
   "accuracy": 62.4,
   "ci": [
    53.7,
    70.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "glm-4.7-flash-q8",
   "profile": "extraction",
   "n": 125,
   "passed": 95,
   "accuracy": 76.0,
   "ci": [
    67.8,
    82.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "granite-4.2-30b-gguf",
   "profile": "extraction",
   "n": 125,
   "passed": 105,
   "accuracy": 84.0,
   "ci": [
    76.6,
    89.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 125,
   "passed": 69,
   "accuracy": 55.2,
   "ci": [
    46.5,
    63.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "lfm2.5-8b-a1b",
   "profile": "extraction",
   "n": 125,
   "passed": 59,
   "accuracy": 47.2,
   "ci": [
    38.7,
    55.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 125,
   "passed": 60,
   "accuracy": 48.0,
   "ci": [
    39.4,
    56.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "minicpm5-2b-q8-np1",
   "profile": "extraction",
   "n": 125,
   "passed": 70,
   "accuracy": 56.0,
   "ci": [
    47.2,
    64.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 125,
   "passed": 78,
   "accuracy": 62.4,
   "ci": [
    53.7,
    70.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "muse-glimmer-30b",
   "profile": "extraction",
   "n": 125,
   "passed": 107,
   "accuracy": 85.6,
   "ci": [
    78.4,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "nemotron-lightning-30b",
   "profile": "extraction",
   "n": 125,
   "passed": 75,
   "accuracy": 60.0,
   "ci": [
    51.2,
    68.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "neohorse-1-4b",
   "profile": "extraction",
   "n": 125,
   "passed": 79,
   "accuracy": 63.2,
   "ci": [
    54.5,
    71.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "ornith-1.5-35b-q6-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 91,
   "accuracy": 72.8,
   "ci": [
    64.4,
    79.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 125,
   "passed": 102,
   "accuracy": 81.6,
   "ci": [
    73.9,
    87.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "ornith-35b-a3b-q40",
   "profile": "extraction",
   "n": 125,
   "passed": 95,
   "accuracy": 76.0,
   "ci": [
    67.8,
    82.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "ornith-9b-kvq4",
   "profile": "extraction",
   "n": 125,
   "passed": 100,
   "accuracy": 80.0,
   "ci": [
    72.1,
    86.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-coder-30b-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 96,
   "accuracy": 76.8,
   "ci": [
    68.7,
    83.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-coder-30b",
   "profile": "extraction",
   "n": 125,
   "passed": 97,
   "accuracy": 77.6,
   "ci": [
    69.5,
    84.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b-a3b-iq4xs-smoke",
   "profile": "extraction",
   "n": 25,
   "passed": 17,
   "accuracy": 68.0,
   "ci": [
    48.4,
    82.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b-a3b-iq4xs",
   "profile": "extraction",
   "n": 125,
   "passed": 111,
   "accuracy": 88.8,
   "ci": [
    82.1,
    93.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b-coder",
   "profile": "extraction",
   "n": 125,
   "passed": 96,
   "accuracy": 76.8,
   "ci": [
    68.7,
    83.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b-reap",
   "profile": "extraction",
   "n": 125,
   "passed": 109,
   "accuracy": 87.2,
   "ci": [
    80.2,
    92.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b-thinking",
   "profile": "extraction",
   "n": 125,
   "passed": 82,
   "accuracy": 65.6,
   "ci": [
    56.9,
    73.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b-thinking",
   "profile": "study-default",
   "n": 1,
   "passed": 1,
   "accuracy": 100.0,
   "ci": [
    20.7,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3-next-80b",
   "profile": "extraction",
   "n": 125,
   "passed": 111,
   "accuracy": 88.8,
   "ci": [
    82.1,
    93.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.5-122b-a10b-iq3",
   "profile": "extraction",
   "n": 125,
   "passed": 101,
   "accuracy": 80.8,
   "ci": [
    73.0,
    86.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.5-4b-base",
   "profile": "extraction",
   "n": 125,
   "passed": 93,
   "accuracy": 74.4,
   "ci": [
    66.1,
    81.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.5-9b-q8-b10618",
   "profile": "extraction",
   "n": 125,
   "passed": 90,
   "accuracy": 72.0,
   "ci": [
    63.6,
    79.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.5-9b-q8",
   "profile": "extraction",
   "n": 125,
   "passed": 90,
   "accuracy": 72.0,
   "ci": [
    63.6,
    79.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.6-35b",
   "profile": "extraction",
   "n": 125,
   "passed": 103,
   "accuracy": 82.4,
   "ci": [
    74.8,
    88.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.8-27b-noreason",
   "profile": "extraction",
   "n": 125,
   "passed": 100,
   "accuracy": 80.0,
   "ci": [
    72.1,
    86.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.8-27b",
   "profile": "extraction",
   "n": 125,
   "passed": 100,
   "accuracy": 80.0,
   "ci": [
    72.1,
    86.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 125,
   "passed": 84,
   "accuracy": 67.2,
   "ci": [
    58.6,
    74.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "qwen38-flash-next",
   "profile": "extraction",
   "n": 125,
   "passed": 99,
   "accuracy": 79.2,
   "ci": [
    71.3,
    85.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 125,
   "passed": 86,
   "accuracy": 68.8,
   "ci": [
    60.2,
    76.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "grounding",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 125,
   "passed": 64,
   "accuracy": 51.2,
   "ci": [
    42.5,
    59.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "dcb396faf8b83b0ac1631207e056bdaf401690ff265473852cde4d5596469991",
   "grader_id": "30b933dcc6a7e2d4"
  },
  {
   "suite": "needle",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 110,
   "passed": 69,
   "accuracy": 62.7,
   "ci": [
    53.4,
    71.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "5c5199b9eee8a595c6cb042a6499235567e577b397f9cc9019c648ac8d6d8b7b",
   "grader_id": "c38dec33aa1c86c2"
  },
  {
   "suite": "needle",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 110,
   "passed": 94,
   "accuracy": 85.5,
   "ci": [
    77.7,
    90.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "5c5199b9eee8a595c6cb042a6499235567e577b397f9cc9019c648ac8d6d8b7b",
   "grader_id": "c38dec33aa1c86c2"
  },
  {
   "suite": "needle",
   "model": "ornith-9b-kv-f16",
   "profile": "extraction",
   "n": 110,
   "passed": 64,
   "accuracy": 58.2,
   "ci": [
    48.8,
    67.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "5c5199b9eee8a595c6cb042a6499235567e577b397f9cc9019c648ac8d6d8b7b",
   "grader_id": "c6ac25d2874c256f"
  },
  {
   "suite": "needle",
   "model": "ornith-9b-kv-q40",
   "profile": "extraction",
   "n": 110,
   "passed": 61,
   "accuracy": 55.5,
   "ci": [
    46.1,
    64.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "5c5199b9eee8a595c6cb042a6499235567e577b397f9cc9019c648ac8d6d8b7b",
   "grader_id": "c38dec33aa1c86c2"
  },
  {
   "suite": "nullschema",
   "model": "glm-4.7-flash-mlx-q4",
   "profile": "extraction",
   "n": 72,
   "passed": 29,
   "accuracy": 40.3,
   "ci": [
    29.7,
    51.8
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "glm-4.7-flash-mlx-q8",
   "profile": "extraction",
   "n": 72,
   "passed": 43,
   "accuracy": 59.7,
   "ci": [
    48.2,
    70.3
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "nemotron-lightning-30b-mlx-4bit",
   "profile": "extraction",
   "n": 72,
   "passed": 7,
   "accuracy": 9.7,
   "ci": [
    4.8,
    18.7
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "ornith-1.5-35b-mlx-4bit",
   "profile": "extraction",
   "n": 72,
   "passed": 45,
   "accuracy": 62.5,
   "ci": [
    51.0,
    72.8
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-8b-mlx-8bit",
   "profile": "extraction",
   "n": 72,
   "passed": 41,
   "accuracy": 56.9,
   "ci": [
    45.4,
    67.7
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-next-80b-mlx-4bit",
   "profile": "extraction",
   "n": 72,
   "passed": 69,
   "accuracy": 95.8,
   "ci": [
    88.5,
    98.6
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "agents-a1-35b-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 28,
   "accuracy": 38.9,
   "ci": [
    28.5,
    50.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 72,
   "passed": 13,
   "accuracy": 18.1,
   "ci": [
    10.9,
    28.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 72,
   "passed": 14,
   "accuracy": 19.4,
   "ci": [
    12.0,
    30.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "bonsai2-27b-pq2",
   "profile": "extraction",
   "n": 72,
   "passed": 23,
   "accuracy": 31.9,
   "ci": [
    22.3,
    43.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "bonsai2-27b-ptq1",
   "profile": "extraction",
   "n": 72,
   "passed": 23,
   "accuracy": 31.9,
   "ci": [
    22.3,
    43.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 72,
   "passed": 32,
   "accuracy": 44.4,
   "ci": [
    33.5,
    55.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "btl-4",
   "profile": "extraction",
   "n": 72,
   "passed": 26,
   "accuracy": 36.1,
   "ci": [
    26.0,
    47.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "devstral-small-2-24b-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 45,
   "accuracy": 62.5,
   "ci": [
    51.0,
    72.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "flashnext-4.27bpw-m64",
   "profile": "extraction",
   "n": 72,
   "passed": 42,
   "accuracy": 58.3,
   "ci": [
    46.8,
    69.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gemma4-12b-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 64,
   "accuracy": 88.9,
   "ci": [
    79.6,
    94.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gemma4-12b-midrange",
   "profile": "extraction",
   "n": 72,
   "passed": 63,
   "accuracy": 87.5,
   "ci": [
    77.9,
    93.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gemma4-12b",
   "profile": "extraction",
   "n": 72,
   "passed": 64,
   "accuracy": 88.9,
   "ci": [
    79.6,
    94.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gemma4-e2b-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 9,
   "accuracy": 12.5,
   "ci": [
    6.7,
    22.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gemma4-e2b",
   "profile": "extraction",
   "n": 72,
   "passed": 9,
   "accuracy": 12.5,
   "ci": [
    6.7,
    22.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gemma4-e4b-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 10,
   "accuracy": 13.9,
   "ci": [
    7.7,
    23.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gemma4-e4b",
   "profile": "extraction",
   "n": 72,
   "passed": 10,
   "accuracy": 13.9,
   "ci": [
    7.7,
    23.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "glm-4.7-flash-q40",
   "profile": "extraction",
   "n": 72,
   "passed": 32,
   "accuracy": 44.4,
   "ci": [
    33.5,
    55.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "glm-4.7-flash-q8",
   "profile": "extraction",
   "n": 72,
   "passed": 35,
   "accuracy": 48.6,
   "ci": [
    37.4,
    59.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "gpt-oss-20b",
   "profile": "extraction",
   "n": 72,
   "passed": 52,
   "accuracy": 72.2,
   "ci": [
    61.0,
    81.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "granite-4.2-30b-gguf",
   "profile": "extraction",
   "n": 72,
   "passed": 65,
   "accuracy": 90.3,
   "ci": [
    81.3,
    95.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-3.7b-q4-precision",
   "profile": "extraction",
   "n": 72,
   "passed": 28,
   "accuracy": 38.9,
   "ci": [
    28.5,
    50.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-3.7b-q8-precision",
   "profile": "extraction",
   "n": 72,
   "passed": 31,
   "accuracy": 43.1,
   "ci": [
    32.3,
    54.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-Q4_1",
   "profile": "extraction",
   "n": 72,
   "passed": 36,
   "accuracy": 50.0,
   "ci": [
    38.7,
    61.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-Q5_0",
   "profile": "extraction",
   "n": 72,
   "passed": 41,
   "accuracy": 56.9,
   "ci": [
    45.4,
    67.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-Q5_1",
   "profile": "extraction",
   "n": 72,
   "passed": 42,
   "accuracy": 58.3,
   "ci": [
    46.8,
    69.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-ctx32k",
   "profile": "extraction",
   "n": 72,
   "passed": 39,
   "accuracy": 54.2,
   "ci": [
    42.7,
    65.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-extraction",
   "profile": "extraction",
   "n": 72,
   "passed": 39,
   "accuracy": 54.2,
   "ci": [
    42.7,
    65.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-q4_0",
   "profile": "extraction",
   "n": 72,
   "passed": 47,
   "accuracy": 65.3,
   "ci": [
    53.8,
    75.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-q8-precision",
   "profile": "extraction",
   "n": 72,
   "passed": 51,
   "accuracy": 70.8,
   "ci": [
    59.5,
    80.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-vendor-k2",
   "profile": "vendor-k2",
   "n": 72,
   "passed": 34,
   "accuracy": 47.2,
   "ci": [
    36.1,
    58.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-36b-vendor-k2b",
   "profile": "vendor-k2b",
   "n": 72,
   "passed": 41,
   "accuracy": 56.9,
   "ci": [
    45.4,
    67.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-4b-bf16-precision",
   "profile": "extraction",
   "n": 72,
   "passed": 31,
   "accuracy": 43.1,
   "ci": [
    32.3,
    54.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-7b-bf16-precision",
   "profile": "extraction",
   "n": 72,
   "passed": 27,
   "accuracy": 37.5,
   "ci": [
    27.2,
    49.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-7b-q4-precision",
   "profile": "extraction",
   "n": 72,
   "passed": 27,
   "accuracy": 37.5,
   "ci": [
    27.2,
    49.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-7b-q8-precision",
   "profile": "extraction",
   "n": 72,
   "passed": 26,
   "accuracy": 36.1,
   "ci": [
    26.0,
    47.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-horizon-3.7b",
   "profile": "extraction",
   "n": 72,
   "passed": 31,
   "accuracy": 43.1,
   "ci": [
    32.3,
    54.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 72,
   "passed": 25,
   "accuracy": 34.7,
   "ci": [
    24.8,
    46.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "lfm2.5-8b-a1b",
   "profile": "extraction",
   "n": 72,
   "passed": 20,
   "accuracy": 27.8,
   "ci": [
    18.8,
    39.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "lfm25-8b-a1b-midrange",
   "profile": "extraction",
   "n": 72,
   "passed": 20,
   "accuracy": 27.8,
   "ci": [
    18.8,
    39.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 72,
   "passed": 23,
   "accuracy": 31.9,
   "ci": [
    22.3,
    43.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "nemotron-lightning-30b",
   "profile": "extraction",
   "n": 72,
   "passed": 11,
   "accuracy": 15.3,
   "ci": [
    8.8,
    25.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "neohorse-1-4b",
   "profile": "extraction",
   "n": 72,
   "passed": 20,
   "accuracy": 27.8,
   "ci": [
    18.8,
    39.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "ornith-1.5-35b-q6-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 25,
   "accuracy": 34.7,
   "ci": [
    24.8,
    46.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 72,
   "passed": 38,
   "accuracy": 52.8,
   "ci": [
    41.4,
    63.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "ornith-35b-a3b-q40",
   "profile": "extraction",
   "n": 72,
   "passed": 26,
   "accuracy": 36.1,
   "ci": [
    26.0,
    47.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "ornith-9b-kvq4",
   "profile": "extraction",
   "n": 72,
   "passed": 41,
   "accuracy": 56.9,
   "ci": [
    45.4,
    67.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-8b-midrange",
   "profile": "extraction",
   "n": 72,
   "passed": 25,
   "accuracy": 34.7,
   "ci": [
    24.8,
    46.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-coder-30b-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 27,
   "accuracy": 37.5,
   "ci": [
    27.2,
    49.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-next-80b-a3b-iq4xs",
   "profile": "extraction",
   "n": 72,
   "passed": 70,
   "accuracy": 97.2,
   "ci": [
    90.4,
    99.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-next-80b-coder",
   "profile": "extraction",
   "n": 72,
   "passed": 41,
   "accuracy": 56.9,
   "ci": [
    45.4,
    67.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-next-80b-reap",
   "profile": "extraction",
   "n": 72,
   "passed": 70,
   "accuracy": 97.2,
   "ci": [
    90.4,
    99.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-next-80b-thinking",
   "profile": "extraction",
   "n": 72,
   "passed": 42,
   "accuracy": 58.3,
   "ci": [
    46.8,
    69.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3-next-80b",
   "profile": "extraction",
   "n": 72,
   "passed": 70,
   "accuracy": 97.2,
   "ci": [
    90.4,
    99.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3.5-122b-a10b-iq3",
   "profile": "extraction",
   "n": 72,
   "passed": 33,
   "accuracy": 45.8,
   "ci": [
    34.8,
    57.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3.5-4b-base",
   "profile": "extraction",
   "n": 72,
   "passed": 24,
   "accuracy": 33.3,
   "ci": [
    23.5,
    44.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3.5-9b-q8-b10618",
   "profile": "extraction",
   "n": 72,
   "passed": 22,
   "accuracy": 30.6,
   "ci": [
    21.1,
    42.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3.6-35b",
   "profile": "extraction",
   "n": 72,
   "passed": 44,
   "accuracy": 61.1,
   "ci": [
    49.6,
    71.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3.8-27b-q4_0",
   "profile": "extraction",
   "n": 72,
   "passed": 50,
   "accuracy": 69.4,
   "ci": [
    58.0,
    78.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 72,
   "passed": 13,
   "accuracy": 18.1,
   "ci": [
    10.9,
    28.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen35-9b-gguf-q40",
   "profile": "extraction",
   "n": 72,
   "passed": 5,
   "accuracy": 6.9,
   "ci": [
    3.0,
    15.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen35-9b-gguf-q4km",
   "profile": "extraction",
   "n": 72,
   "passed": 17,
   "accuracy": 23.6,
   "ci": [
    15.3,
    34.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen35-9b-mlx-affine-g32",
   "profile": "extraction",
   "n": 72,
   "passed": 33,
   "accuracy": 45.8,
   "ci": [
    34.8,
    57.3
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen35-9b-mlx-affine-g64",
   "profile": "extraction",
   "n": 72,
   "passed": 43,
   "accuracy": 59.7,
   "ci": [
    48.2,
    70.3
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen35-9b-mlx-mxfp4",
   "profile": "extraction",
   "n": 72,
   "passed": 25,
   "accuracy": 34.7,
   "ci": [
    24.8,
    46.2
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen38-27b-np1",
   "profile": "extraction",
   "n": 72,
   "passed": 55,
   "accuracy": 76.4,
   "ci": [
    65.4,
    84.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen38-flash-next",
   "profile": "extraction",
   "n": 72,
   "passed": 36,
   "accuracy": 50.0,
   "ci": [
    38.7,
    61.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen38-gsqrco-iq3s",
   "profile": "extraction",
   "n": 72,
   "passed": 45,
   "accuracy": 62.5,
   "ci": [
    51.0,
    72.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "qwen38-rebase-b10893",
   "profile": "extraction",
   "n": 72,
   "passed": 55,
   "accuracy": 76.4,
   "ci": [
    65.4,
    84.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "reap-60b-20260910",
   "profile": "extraction",
   "n": 72,
   "passed": 34,
   "accuracy": 47.2,
   "ci": [
    36.1,
    58.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "reap-60b-mlx-4bit-uniform",
   "profile": "extraction",
   "n": 72,
   "passed": 61,
   "accuracy": 84.7,
   "ci": [
    74.7,
    91.2
   ],
   "runtime": "mlx",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "spark-x25-4b",
   "profile": "extraction",
   "n": 72,
   "passed": 35,
   "accuracy": 48.6,
   "ci": [
    37.4,
    59.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 72,
   "passed": 20,
   "accuracy": 27.8,
   "ci": [
    18.8,
    39.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "nullschema",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 72,
   "passed": 8,
   "accuracy": 11.1,
   "ci": [
    5.7,
    20.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "3b91280bb40372efb3ae6e98ba2b1b46b768143cb51cf1dcf9870d90dbff84b2",
   "grader_id": "d7448e0f5fc3f9af"
  },
  {
   "suite": "screening",
   "model": "glm-4.7-flash-mlx-mixed_3_6",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "glm-4.7-flash-mlx-mixed_4_6",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "glm-4.7-flash-mlx-q4",
   "profile": "extraction",
   "n": 60,
   "passed": 58,
   "accuracy": 96.7,
   "ci": [
    88.6,
    99.1
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "glm-4.7-flash-mlx-q8",
   "profile": "extraction",
   "n": 60,
   "passed": 58,
   "accuracy": 96.7,
   "ci": [
    88.6,
    99.1
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-4.2-30b-mlx-q4",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian-4.1-8b-mlx-bf16",
   "profile": "extraction",
   "n": 60,
   "passed": 59,
   "accuracy": 98.3,
   "ci": [
    91.1,
    99.7
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian-4.1-8b-mlx-mixed36",
   "profile": "extraction",
   "n": 60,
   "passed": 57,
   "accuracy": 95.0,
   "ci": [
    86.3,
    98.3
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian-4.1-8b-mlx-q8",
   "profile": "extraction",
   "n": 60,
   "passed": 59,
   "accuracy": 98.3,
   "ci": [
    91.1,
    99.7
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "laguna-xs2-mlx-q4",
   "profile": "extraction",
   "n": 11,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    25.9
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "nemotron-lightning-30b-mlx-4bit",
   "profile": "extraction",
   "n": 60,
   "passed": 54,
   "accuracy": 90.0,
   "ci": [
    79.9,
    95.3
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "ornith-1.5-35b-mlx-4bit",
   "profile": "extraction",
   "n": 60,
   "passed": 53,
   "accuracy": 88.3,
   "ci": [
    77.8,
    94.2
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-8b-mlx-8bit",
   "profile": "extraction",
   "n": 60,
   "passed": 58,
   "accuracy": 96.7,
   "ci": [
    88.6,
    99.1
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b-mlx-4bit",
   "profile": "extraction",
   "n": 60,
   "passed": 58,
   "accuracy": 96.7,
   "ci": [
    88.6,
    99.1
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b-reap-mlx-mixed36",
   "profile": "extraction",
   "n": 60,
   "passed": 59,
   "accuracy": 98.3,
   "ci": [
    91.1,
    99.7
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b-reap-mlx-q4",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3.8-27b-mlx-4bit",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "agents-a1-35b-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 57,
   "accuracy": 95.0,
   "ci": [
    86.3,
    98.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 60,
   "passed": 58,
   "accuracy": 96.7,
   "ci": [
    88.6,
    99.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 60,
   "passed": 52,
   "accuracy": 86.7,
   "ci": [
    75.8,
    93.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "bonsai2-27b-pq2",
   "profile": "extraction",
   "n": 60,
   "passed": 59,
   "accuracy": 98.3,
   "ci": [
    91.1,
    99.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "bonsai2-27b-ptq1",
   "profile": "extraction",
   "n": 60,
   "passed": 59,
   "accuracy": 98.3,
   "ci": [
    91.1,
    99.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "btl-4-q4km-recheck",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "btl-4",
   "profile": "extraction",
   "n": 60,
   "passed": 57,
   "accuracy": 95.0,
   "ci": [
    86.3,
    98.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "devstral-small-2-24b-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "edge0-35b-recheck",
   "profile": "extraction",
   "n": 60,
   "passed": 53,
   "accuracy": 88.3,
   "ci": [
    77.8,
    94.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 60,
   "passed": 53,
   "accuracy": 88.3,
   "ci": [
    77.8,
    94.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "flashnext-4.27bpw-m64",
   "profile": "extraction",
   "n": 60,
   "passed": 57,
   "accuracy": 95.0,
   "ci": [
    86.3,
    98.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "gemma4-12b-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "gemma4-12b-recheck",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "gemma4-12b",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "gemma4-e2b-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "gemma4-e2b",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "gemma4-e4b-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "gemma4-e4b",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "glm-4.7-flash-q8",
   "profile": "extraction",
   "n": 60,
   "passed": 57,
   "accuracy": 95.0,
   "ci": [
    86.3,
    98.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-4.2-30b-gguf",
   "profile": "extraction",
   "n": 60,
   "passed": 59,
   "accuracy": 98.3,
   "ci": [
    91.1,
    99.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian-3.1-2b",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian-4.1-8b",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian-gguf-q4km",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian-mlx-mixed36",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "granite-guardian",
   "profile": "extraction",
   "n": 60,
   "passed": 22,
   "accuracy": 36.7,
   "ci": [
    25.6,
    49.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "guardian-mixed36-mlxlm",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "k2-36b-ctx32k",
   "profile": "extraction",
   "n": 60,
   "passed": 54,
   "accuracy": 90.0,
   "ci": [
    79.9,
    95.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "k2-horizon-3.7b",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 60,
   "passed": 54,
   "accuracy": 90.0,
   "ci": [
    79.9,
    95.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "lfm2.5-8b-a1b",
   "profile": "extraction",
   "n": 60,
   "passed": 44,
   "accuracy": 73.3,
   "ci": [
    61.0,
    82.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "minicpm5-2b-q8-np1",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 60,
   "passed": 51,
   "accuracy": 85.0,
   "ci": [
    73.9,
    91.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "mlx-community-Qwen3.6-35B-A3B-4bit",
   "profile": "extraction",
   "n": 60,
   "passed": 54,
   "accuracy": 90.0,
   "ci": [
    79.9,
    95.3
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "muse-glimmer-30b",
   "profile": "extraction",
   "n": 60,
   "passed": 52,
   "accuracy": 86.7,
   "ci": [
    75.8,
    93.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "nemotron-lightning-30b",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "ornith-1.5-35b-q6-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 57,
   "accuracy": 95.0,
   "ci": [
    86.3,
    98.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-coder-30b-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b-a3b-iq4xs",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b-coder",
   "profile": "extraction",
   "n": 60,
   "passed": 54,
   "accuracy": 90.0,
   "ci": [
    79.9,
    95.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b-reap",
   "profile": "extraction",
   "n": 60,
   "passed": 59,
   "accuracy": 98.3,
   "ci": [
    91.1,
    99.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b-thinking",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3-next-80b",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3.5-122b-a10b-iq3",
   "profile": "extraction",
   "n": 60,
   "passed": 53,
   "accuracy": 88.3,
   "ci": [
    77.8,
    94.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3.5-9b-q8-b10618",
   "profile": "extraction",
   "n": 60,
   "passed": 58,
   "accuracy": 96.7,
   "ci": [
    88.6,
    99.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3.6-35b-swiftlm",
   "profile": "extraction",
   "n": 60,
   "passed": 53,
   "accuracy": 88.3,
   "ci": [
    77.8,
    94.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3.6-35b",
   "profile": "extraction",
   "n": 60,
   "passed": 52,
   "accuracy": 86.7,
   "ci": [
    75.8,
    93.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3.8-9b-distill-recheck",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 60,
   "passed": 55,
   "accuracy": 91.7,
   "ci": [
    81.9,
    96.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen38-27b-q3kxl-chad",
   "profile": "extraction",
   "n": 60,
   "passed": 28,
   "accuracy": 46.7,
   "ci": [
    34.6,
    59.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "qwen38-flash-next",
   "profile": "extraction",
   "n": 60,
   "passed": 58,
   "accuracy": 96.7,
   "ci": [
    88.6,
    99.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "reapmix36-rapid-mlx",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "reapq4-mlx_lm",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "reapq4-rapid-mlx",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "mlx",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "ternary-bonsai-27b-recheck",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "screening",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 60,
   "passed": 52,
   "accuracy": 86.7,
   "ci": [
    75.8,
    93.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "64c97ca2269c29afe26cb1fd083655b2b53a2d596c300ae60fd19d4f0fa2bdca",
   "grader_id": "0661b49a10be2d2a"
  },
  {
   "suite": "shapegen",
   "model": "qwen3-coder-30b",
   "profile": "extraction",
   "n": 12,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    24.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "fc27d4e1a999c675210e8acbfabc7869a451a019d7c4d12caa9b08aed106325a",
   "grader_id": "f23222ad8df22fd8"
  },
  {
   "suite": "sitebuild",
   "model": "qwen3-coder-30b",
   "profile": "agentic-fast",
   "n": 1,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    0.0,
    79.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "8b54725d2778dc60aa6466c363b621951ec3394a9d46b19e1404f6fb9bdccc4a",
   "grader_id": "b2c603d6c0d6afb3"
  },
  {
   "suite": "synthesis",
   "model": "qwen3-next-80b-reap-mlx-mixed36",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "760936a5348b2ffd1847558aaca56d627279953e89698443ebb24d3af5a0564c",
   "grader_id": "27df090db4445c2c"
  },
  {
   "suite": "synthesis",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 60,
   "passed": 21,
   "accuracy": 35.0,
   "ci": [
    24.2,
    47.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 60,
   "passed": 40,
   "accuracy": 66.7,
   "ci": [
    54.1,
    77.3
   ],
   "runtime": "mlx",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 60,
   "passed": 40,
   "accuracy": 66.7,
   "ci": [
    54.1,
    77.3
   ],
   "runtime": "mlx",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 60,
   "passed": 39,
   "accuracy": 65.0,
   "ci": [
    52.4,
    75.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "bonsai2-27b-pq2",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "bonsai2-27b-ptq1",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "btl-4",
   "profile": "extraction",
   "n": 60,
   "passed": 48,
   "accuracy": 80.0,
   "ci": [
    68.2,
    88.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "diffusiongemma-26b-mlx",
   "profile": "extraction",
   "n": 60,
   "passed": 48,
   "accuracy": 80.0,
   "ci": [
    68.2,
    88.2
   ],
   "runtime": "mlx",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 60,
   "passed": 49,
   "accuracy": 81.7,
   "ci": [
    70.1,
    89.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "gemma4-12b-b10893",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "gemma4-12b-midrange",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "gemma4-12b",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "glm-4.7-flash-q40",
   "profile": "extraction",
   "n": 60,
   "passed": 36,
   "accuracy": 60.0,
   "ci": [
    47.4,
    71.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-3.7b-q4-precision",
   "profile": "extraction",
   "n": 60,
   "passed": 30,
   "accuracy": 50.0,
   "ci": [
    37.7,
    62.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-3.7b-q8-precision",
   "profile": "extraction",
   "n": 60,
   "passed": 34,
   "accuracy": 56.7,
   "ci": [
    44.1,
    68.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-3.7b",
   "profile": "extraction",
   "n": 60,
   "passed": 35,
   "accuracy": 58.3,
   "ci": [
    45.7,
    69.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-36b-a4b-q4",
   "profile": "extraction",
   "n": 60,
   "passed": 44,
   "accuracy": 73.3,
   "ci": [
    61.0,
    82.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-36b-ctx32k",
   "profile": "extraction",
   "n": 60,
   "passed": 42,
   "accuracy": 70.0,
   "ci": [
    57.5,
    80.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-36b-extraction",
   "profile": "extraction",
   "n": 60,
   "passed": 45,
   "accuracy": 75.0,
   "ci": [
    62.8,
    84.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-36b-q4_0",
   "profile": "extraction",
   "n": 60,
   "passed": 46,
   "accuracy": 76.7,
   "ci": [
    64.6,
    85.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-36b-vendor-k2",
   "profile": "vendor-k2",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-36b-vendor-k2b",
   "profile": "vendor-k2b",
   "n": 60,
   "passed": 54,
   "accuracy": 90.0,
   "ci": [
    79.9,
    95.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-4b-bf16-precision",
   "profile": "extraction",
   "n": 60,
   "passed": 34,
   "accuracy": 56.7,
   "ci": [
    44.1,
    68.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "k2-7b",
   "profile": "extraction",
   "n": 60,
   "passed": 45,
   "accuracy": 75.0,
   "ci": [
    62.8,
    84.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "lfm25-8b-a1b-midrange",
   "profile": "extraction",
   "n": 60,
   "passed": 32,
   "accuracy": 53.3,
   "ci": [
    40.9,
    65.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 60,
   "passed": 45,
   "accuracy": 75.0,
   "ci": [
    62.8,
    84.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "minicpm5-2b-q8-np1",
   "profile": "extraction",
   "n": 60,
   "passed": 47,
   "accuracy": 78.3,
   "ci": [
    66.4,
    86.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 60,
   "passed": 36,
   "accuracy": 60.0,
   "ci": [
    47.4,
    71.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 60,
   "passed": 48,
   "accuracy": 80.0,
   "ci": [
    68.2,
    88.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "qwen3-8b-midrange",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "qwen3.8-27b-q4_0",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "qwen38-27b-np1",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "qwen38-27b-q3kxl-chad",
   "profile": "extraction",
   "n": 60,
   "passed": 51,
   "accuracy": 85.0,
   "ci": [
    73.9,
    91.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "qwen38-gsqrco-iq3s",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "reap-60b-20260910",
   "profile": "extraction",
   "n": 60,
   "passed": 50,
   "accuracy": 83.3,
   "ci": [
    72.0,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "reap-60b-gguf-q4km",
   "profile": "extraction",
   "n": 60,
   "passed": 49,
   "accuracy": 81.7,
   "ci": [
    70.1,
    89.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "reap-60b-mlx-4bit-uniform",
   "profile": "extraction",
   "n": 60,
   "passed": 51,
   "accuracy": 85.0,
   "ci": [
    73.9,
    91.9
   ],
   "runtime": "mlx",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "reap-60b",
   "profile": "extraction",
   "n": 60,
   "passed": 49,
   "accuracy": 81.7,
   "ci": [
    70.1,
    89.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "spark-x25-4b",
   "profile": "extraction",
   "n": 60,
   "passed": 17,
   "accuracy": 28.3,
   "ci": [
    18.5,
    40.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 60,
   "passed": 40,
   "accuracy": 66.7,
   "ci": [
    54.1,
    77.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "synthesis",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 60,
   "passed": 36,
   "accuracy": 60.0,
   "ci": [
    47.4,
    71.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "267d1954e225c5b63c99367e900464f5d6fb9cb19e6654dba710fed8bcb8779c",
   "grader_id": "4156dd3c13361e8b"
  },
  {
   "suite": "tagger",
   "model": "gemma4-e2b-mlx-4bit",
   "profile": "extraction",
   "n": 240,
   "passed": 206,
   "accuracy": 85.8,
   "ci": [
    80.9,
    89.7
   ],
   "runtime": "mlx",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "tagger-e2b-v1-dl-tagger-e2b-v1",
   "profile": "extraction",
   "n": 240,
   "passed": 178,
   "accuracy": 74.2,
   "ci": [
    68.3,
    79.3
   ],
   "runtime": "mlx",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 240,
   "passed": 205,
   "accuracy": 85.4,
   "ci": [
    80.4,
    89.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 240,
   "passed": 210,
   "accuracy": 87.5,
   "ci": [
    82.7,
    91.1
   ],
   "runtime": "mlx",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 240,
   "passed": 211,
   "accuracy": 87.9,
   "ci": [
    83.2,
    91.5
   ],
   "runtime": "mlx",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 240,
   "passed": 68,
   "accuracy": 28.3,
   "ci": [
    23.0,
    34.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 240,
   "passed": 209,
   "accuracy": 87.1,
   "ci": [
    82.2,
    90.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "btl-4",
   "profile": "extraction",
   "n": 240,
   "passed": 204,
   "accuracy": 85.0,
   "ci": [
    79.9,
    89.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 240,
   "passed": 212,
   "accuracy": 88.3,
   "ci": [
    83.7,
    91.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "gemma4-12b-ab",
   "profile": "extraction",
   "n": 240,
   "passed": 225,
   "accuracy": 93.8,
   "ci": [
    89.9,
    96.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "gemma4-12b-b10618",
   "profile": "extraction",
   "n": 240,
   "passed": 225,
   "accuracy": 93.8,
   "ci": [
    89.9,
    96.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "gemma4-12b",
   "profile": "study-nothink",
   "n": 240,
   "passed": 180,
   "accuracy": 75.0,
   "ci": [
    69.2,
    80.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": null,
   "grader_id": null
  },
  {
   "suite": "tagger",
   "model": "gemma4-e2b-ab",
   "profile": "extraction",
   "n": 240,
   "passed": 219,
   "accuracy": 91.2,
   "ci": [
    87.0,
    94.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "gemma4-e2b",
   "profile": "study-nothink",
   "n": 240,
   "passed": 219,
   "accuracy": 91.2,
   "ci": [
    87.0,
    94.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": null,
   "grader_id": null
  },
  {
   "suite": "tagger",
   "model": "gemma4-e4b",
   "profile": "study-nothink",
   "n": 480,
   "passed": 218,
   "accuracy": 45.4,
   "ci": [
    41.0,
    49.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": null,
   "grader_id": null
  },
  {
   "suite": "tagger",
   "model": "gpt-oss-20b",
   "profile": "extraction",
   "n": 240,
   "passed": 207,
   "accuracy": 86.2,
   "ci": [
    81.3,
    90.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 240,
   "passed": 183,
   "accuracy": 76.2,
   "ci": [
    70.5,
    81.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "minicpm5-2b-q8-nojinja",
   "profile": "extraction",
   "n": 240,
   "passed": 183,
   "accuracy": 76.2,
   "ci": [
    70.5,
    81.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "minicpm5-2b-q8-np1",
   "profile": "extraction",
   "n": 240,
   "passed": 184,
   "accuracy": 76.7,
   "ci": [
    70.9,
    81.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "minicpm5-2b-q8-np4-today",
   "profile": "extraction",
   "n": 240,
   "passed": 183,
   "accuracy": 76.2,
   "ci": [
    70.5,
    81.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 240,
   "passed": 124,
   "accuracy": 51.7,
   "ci": [
    45.4,
    57.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "ornith-35b-tagger",
   "profile": "extraction",
   "n": 240,
   "passed": 206,
   "accuracy": 85.8,
   "ci": [
    80.9,
    89.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "qwen3-next-80b-tag",
   "profile": "extraction",
   "n": 240,
   "passed": 224,
   "accuracy": 93.3,
   "ci": [
    89.4,
    95.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "qwen3.6-35b-tag",
   "profile": "extraction",
   "n": 240,
   "passed": 218,
   "accuracy": 90.8,
   "ci": [
    86.5,
    93.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 240,
   "passed": 200,
   "accuracy": 83.3,
   "ci": [
    78.1,
    87.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "qwen3.8-iq1s",
   "profile": "study-nothink",
   "n": 129,
   "passed": 18,
   "accuracy": 14.0,
   "ci": [
    9.0,
    21.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "956e03bbffa79aa4"
  },
  {
   "suite": "tagger",
   "model": "tagger-e2b-v1",
   "profile": "extraction",
   "n": 240,
   "passed": 185,
   "accuracy": 77.1,
   "ci": [
    71.4,
    81.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": null,
   "grader_id": null
  },
  {
   "suite": "tagger",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 240,
   "passed": 206,
   "accuracy": 85.8,
   "ci": [
    80.9,
    89.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 240,
   "passed": 105,
   "accuracy": 43.8,
   "ci": [
    37.6,
    50.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "7ef587bf33e5788ac8eb405e52495c6898271491e4611286f3c41f66150e119d",
   "grader_id": "63e04d139a0e5ed3"
  },
  {
   "suite": "tagger_nullable",
   "model": "gemma4-e2b-mlx-4bit",
   "profile": "extraction",
   "n": 240,
   "passed": 177,
   "accuracy": 73.8,
   "ci": [
    67.8,
    78.9
   ],
   "runtime": "mlx",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "tagger-e2b-v1-dl-tagger-e2b-v1",
   "profile": "extraction",
   "n": 240,
   "passed": 180,
   "accuracy": 75.0,
   "ci": [
    69.2,
    80.1
   ],
   "runtime": "mlx",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 240,
   "passed": 218,
   "accuracy": 90.8,
   "ci": [
    86.5,
    93.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 240,
   "passed": 213,
   "accuracy": 88.8,
   "ci": [
    84.1,
    92.2
   ],
   "runtime": "mlx",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 240,
   "passed": 214,
   "accuracy": 89.2,
   "ci": [
    84.6,
    92.5
   ],
   "runtime": "mlx",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 240,
   "passed": 100,
   "accuracy": 41.7,
   "ci": [
    35.6,
    48.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 240,
   "passed": 117,
   "accuracy": 48.8,
   "ci": [
    42.5,
    55.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "btl-4",
   "profile": "extraction",
   "n": 240,
   "passed": 220,
   "accuracy": 91.7,
   "ci": [
    87.5,
    94.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 240,
   "passed": 220,
   "accuracy": 91.7,
   "ci": [
    87.5,
    94.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "gemma4-12b-ab",
   "profile": "extraction",
   "n": 240,
   "passed": 235,
   "accuracy": 97.9,
   "ci": [
    95.2,
    99.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "gemma4-12b-b10618",
   "profile": "extraction",
   "n": 240,
   "passed": 235,
   "accuracy": 97.9,
   "ci": [
    95.2,
    99.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "gemma4-e2b-ab",
   "profile": "extraction",
   "n": 240,
   "passed": 217,
   "accuracy": 90.4,
   "ci": [
    86.0,
    93.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "gpt-oss-20b-study-default",
   "profile": "study-default",
   "n": 35,
   "passed": 31,
   "accuracy": 88.6,
   "ci": [
    74.0,
    95.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "gpt-oss-20b",
   "profile": "extraction",
   "n": 240,
   "passed": 204,
   "accuracy": 85.0,
   "ci": [
    79.9,
    89.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 240,
   "passed": 111,
   "accuracy": 46.2,
   "ci": [
    40.1,
    52.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "minicpm5-2b-q8-np1",
   "profile": "extraction",
   "n": 240,
   "passed": 127,
   "accuracy": 52.9,
   "ci": [
    46.6,
    59.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 240,
   "passed": 55,
   "accuracy": 22.9,
   "ci": [
    18.1,
    28.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "neohorse-1-4b",
   "profile": "extraction",
   "n": 240,
   "passed": 207,
   "accuracy": 86.2,
   "ci": [
    81.3,
    90.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "qwen3-next-80b-tag",
   "profile": "extraction",
   "n": 240,
   "passed": 217,
   "accuracy": 90.4,
   "ci": [
    86.0,
    93.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "qwen3.5-4b-base",
   "profile": "extraction",
   "n": 240,
   "passed": 225,
   "accuracy": 93.8,
   "ci": [
    89.9,
    96.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "qwen3.6-35b-tag",
   "profile": "extraction",
   "n": 240,
   "passed": 222,
   "accuracy": 92.5,
   "ci": [
    88.5,
    95.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 240,
   "passed": 216,
   "accuracy": 90.0,
   "ci": [
    85.6,
    93.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 240,
   "passed": 216,
   "accuracy": 90.0,
   "ci": [
    85.6,
    93.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "tagger_nullable",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 240,
   "passed": 147,
   "accuracy": 61.2,
   "ci": [
    55.0,
    67.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "db3addf23a2bc4ce4c5329bff23b79b7ecea8ba924312a752b771711fec3ac6e",
   "grader_id": "04e875431e26c4b5"
  },
  {
   "suite": "toolcall",
   "model": "qwen3-next-80b-reap-mlx-mixed36",
   "profile": "extraction",
   "n": 60,
   "passed": 47,
   "accuracy": 78.3,
   "ci": [
    66.4,
    86.9
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen3.8-27b-mlx-4bit",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "bonsai2-27b-pq2",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "bonsai2-27b-ptq1",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 60,
   "passed": 56,
   "accuracy": 93.3,
   "ci": [
    84.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "btl-4",
   "profile": "extraction",
   "n": 60,
   "passed": 46,
   "accuracy": 76.7,
   "ci": [
    64.6,
    85.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "diffusiongemma-26b-mlx",
   "profile": "extraction",
   "n": 60,
   "passed": 3,
   "accuracy": 5.0,
   "ci": [
    1.7,
    13.7
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "gemma4-12b-midrange",
   "profile": "extraction",
   "n": 60,
   "passed": 33,
   "accuracy": 55.0,
   "ci": [
    42.5,
    66.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "glm-4.7-flash-q40",
   "profile": "extraction",
   "n": 60,
   "passed": 23,
   "accuracy": 38.3,
   "ci": [
    27.1,
    51.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-3.7b-q4-precision",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-3.7b-q8-precision",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-36b-a4b-q4",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-36b-ctx32k",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-36b-np1",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-36b-q4_0",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-4b-bf16-precision",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-horizon-3.7b",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 60,
   "passed": 57,
   "accuracy": 95.0,
   "ci": [
    86.3,
    98.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "lfm25-8b-a1b-midrange",
   "profile": "extraction",
   "n": 60,
   "passed": 1,
   "accuracy": 1.7,
   "ci": [
    0.3,
    8.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 60,
   "passed": 44,
   "accuracy": 73.3,
   "ci": [
    61.0,
    82.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "mlx-community-Qwen3.6-35B-A3B-4bit",
   "profile": "extraction",
   "n": 60,
   "passed": 36,
   "accuracy": 60.0,
   "ci": [
    47.4,
    71.4
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "neohorse-1-4b",
   "profile": "extraction",
   "n": 60,
   "passed": 34,
   "accuracy": 56.7,
   "ci": [
    44.1,
    68.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "ornith-35b-a3b-q40",
   "profile": "extraction",
   "n": 60,
   "passed": 48,
   "accuracy": 80.0,
   "ci": [
    68.2,
    88.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "ornith-9b-kvq4",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen3-8b-midrange",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen3.5-4b-base",
   "profile": "extraction",
   "n": 60,
   "passed": 22,
   "accuracy": 36.7,
   "ci": [
    25.6,
    49.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen3.8-27b-q4_0",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen3.8-27b",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen38-27b-np1",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "qwen38-gsqrco-iq3s",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "reap-60b-20260910",
   "profile": "extraction",
   "n": 60,
   "passed": 47,
   "accuracy": 78.3,
   "ci": [
    66.4,
    86.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "reap-60b-4bit-repro",
   "profile": "extraction",
   "n": 60,
   "passed": 15,
   "accuracy": 25.0,
   "ci": [
    15.8,
    37.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "reap-60b-gguf-q4km",
   "profile": "extraction",
   "n": 60,
   "passed": 25,
   "accuracy": 41.7,
   "ci": [
    30.1,
    54.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "reap-60b-mlx-4bit-uniform",
   "profile": "extraction-t07",
   "n": 60,
   "passed": 17,
   "accuracy": 28.3,
   "ci": [
    18.5,
    40.8
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "reap-60b-mlx-4bit-uniform",
   "profile": "extraction",
   "n": 60,
   "passed": 15,
   "accuracy": 25.0,
   "ci": [
    15.8,
    37.2
   ],
   "runtime": "mlx",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "spark-x25-4b",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 60,
   "passed": 60,
   "accuracy": 100.0,
   "ci": [
    94.0,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "toolcall",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 60,
   "passed": 0,
   "accuracy": 0.0,
   "ci": [
    -0.0,
    6.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "10af88c170513155a775a8941ef522dfad1fbfc19693f7757a20392d3d6587e2",
   "grader_id": "804e8fc9457649d8"
  },
  {
   "suite": "tools",
   "model": "agents-a1-35b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "d6a32c09e57bea7b"
  },
  {
   "suite": "tools",
   "model": "bonsai-27b-1bit",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "bonsai-8b-1bit",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 14,
   "accuracy": 93.3,
   "ci": [
    70.2,
    98.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "btl-4-q4km",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "btl-4",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "gemma4-12b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 13,
   "accuracy": 86.7,
   "ci": [
    62.1,
    96.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "d6a32c09e57bea7b"
  },
  {
   "suite": "tools",
   "model": "gemma4-e2b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "d6a32c09e57bea7b"
  },
  {
   "suite": "tools",
   "model": "gemma4-e4b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "d6a32c09e57bea7b"
  },
  {
   "suite": "tools",
   "model": "k2-horizon-3.7b",
   "profile": "extraction",
   "n": 15,
   "passed": 13,
   "accuracy": 86.7,
   "ci": [
    62.1,
    96.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "minicpm5-2b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 14,
   "accuracy": 93.3,
   "ci": [
    70.2,
    98.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "qwen-agentworld-35b",
   "profile": "extraction",
   "n": 15,
   "passed": 12,
   "accuracy": 80.0,
   "ci": [
    54.8,
    93.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "qwen3-next-80b-ag",
   "profile": "extraction",
   "n": 15,
   "passed": 14,
   "accuracy": 93.3,
   "ci": [
    70.2,
    98.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "qwen3-next-80b-reap-ag",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "qwen3.6-35b-ag",
   "profile": "extraction",
   "n": 15,
   "passed": 14,
   "accuracy": 93.3,
   "ci": [
    70.2,
    98.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "qwen3.8-27b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "d6a32c09e57bea7b"
  },
  {
   "suite": "tools",
   "model": "qwen3.8-9b-distill",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "qwen3.8-iq1s",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 10,
   "accuracy": 66.7,
   "ci": [
    41.7,
    84.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "d6a32c09e57bea7b"
  },
  {
   "suite": "tools",
   "model": "ternary-bonsai-27b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 15,
   "accuracy": 100.0,
   "ci": [
    79.6,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "tools",
   "model": "ternary-bonsai-8b",
   "profile": "agentic-fast",
   "n": 15,
   "passed": 14,
   "accuracy": 93.3,
   "ci": [
    70.2,
    98.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "33a44812f0ad4c394857ceac8e6666c156d4f975c0216ff8006ebc68cc7cc6b3",
   "grader_id": "2763675a5c3da564"
  },
  {
   "suite": "toolscale",
   "model": "agents-a1-35b",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "1bae1f3e1b606eae"
  },
  {
   "suite": "toolscale",
   "model": "bonsai-27b-1bit",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "bonsai-8b-1bit",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "bonsai2-27b-pq2",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 39,
   "accuracy": 97.5,
   "ci": [
    87.1,
    99.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "bonsai2-27b-ptq1",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 39,
   "accuracy": 97.5,
   "ci": [
    87.1,
    99.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "btl-4-q4km",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "btl-4",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "diffusiongemma-26b-mlx",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "mlx",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "gemma4-12b-midrange",
   "profile": "extraction",
   "n": 40,
   "passed": 38,
   "accuracy": 95.0,
   "ci": [
    83.5,
    98.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "gemma4-12b",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 36,
   "accuracy": 90.0,
   "ci": [
    76.9,
    96.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "1bae1f3e1b606eae"
  },
  {
   "suite": "toolscale",
   "model": "gemma4-e2b",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "1bae1f3e1b606eae"
  },
  {
   "suite": "toolscale",
   "model": "gemma4-e4b",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "1bae1f3e1b606eae"
  },
  {
   "suite": "toolscale",
   "model": "glm-4.7-flash-q40",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-3.7b-q4-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-3.7b-q8-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-36b-a4b-q4",
   "profile": "extraction",
   "n": 40,
   "passed": 36,
   "accuracy": 90.0,
   "ci": [
    76.9,
    96.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-36b-ctx32k",
   "profile": "extraction",
   "n": 40,
   "passed": 36,
   "accuracy": 90.0,
   "ci": [
    76.9,
    96.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-36b-np1",
   "profile": "extraction",
   "n": 40,
   "passed": 35,
   "accuracy": 87.5,
   "ci": [
    73.9,
    94.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-36b-q4_0",
   "profile": "extraction",
   "n": 40,
   "passed": 36,
   "accuracy": 90.0,
   "ci": [
    76.9,
    96.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-4b-bf16-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-horizon-3.7b",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "k2-horizon-7b",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "lfm25-8b-a1b-midrange",
   "profile": "extraction",
   "n": 40,
   "passed": 33,
   "accuracy": 82.5,
   "ci": [
    68.0,
    91.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "minicpm5-2b",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "neohorse-1-4b",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 40,
   "passed": 38,
   "accuracy": 95.0,
   "ci": [
    83.5,
    98.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "ornith-35b-a3b-q40",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen-agentworld-35b",
   "profile": "extraction",
   "n": 40,
   "passed": 29,
   "accuracy": 72.5,
   "ci": [
    57.2,
    83.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen3-8b-midrange",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen3-next-80b-ag",
   "profile": "extraction",
   "n": 40,
   "passed": 38,
   "accuracy": 95.0,
   "ci": [
    83.5,
    98.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen3-next-80b-reap-ag",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 36,
   "accuracy": 90.0,
   "ci": [
    76.9,
    96.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen3.5-4b-base",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen3.6-35b-ag",
   "profile": "extraction",
   "n": 40,
   "passed": 32,
   "accuracy": 80.0,
   "ci": [
    65.2,
    89.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen3.8-27b-q4_0",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen3.8-9b-distill",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen38-27b-np1",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "qwen38-gsqrco-iq3s",
   "profile": "extraction",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "reap-60b-20260910",
   "profile": "extraction",
   "n": 40,
   "passed": 38,
   "accuracy": 95.0,
   "ci": [
    83.5,
    98.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "reap-60b-gguf-q4km",
   "profile": "extraction",
   "n": 40,
   "passed": 35,
   "accuracy": 87.5,
   "ci": [
    73.9,
    94.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "reap-60b-mlx-4bit-uniform",
   "profile": "extraction",
   "n": 40,
   "passed": 38,
   "accuracy": 95.0,
   "ci": [
    83.5,
    98.6
   ],
   "runtime": "mlx",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "spark-x25-4b",
   "profile": "extraction",
   "n": 40,
   "passed": 38,
   "accuracy": 95.0,
   "ci": [
    83.5,
    98.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "ternary-bonsai-27b",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "toolscale",
   "model": "ternary-bonsai-8b",
   "profile": "agentic-fast",
   "n": 40,
   "passed": 40,
   "accuracy": 100.0,
   "ci": [
    91.2,
    100.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "b24abb108c40917887fbcc7c3d158dc721d4976945a591952aa883f42ec6a2dd",
   "grader_id": "a2bc3751abfa28e0"
  },
  {
   "suite": "worldview",
   "model": "bonsai-27b-1bit",
   "profile": "extraction",
   "n": 40,
   "passed": 16,
   "accuracy": 40.0,
   "ci": [
    26.3,
    55.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "bonsai-27b-mlx2-cortext",
   "profile": "extraction",
   "n": 40,
   "passed": 17,
   "accuracy": 42.5,
   "ci": [
    28.5,
    57.8
   ],
   "runtime": "mlx",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "bonsai-27b-mlx2-m4pro",
   "profile": "extraction",
   "n": 40,
   "passed": 17,
   "accuracy": 42.5,
   "ci": [
    28.5,
    57.8
   ],
   "runtime": "mlx",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "bonsai-8b-1bit",
   "profile": "extraction",
   "n": 40,
   "passed": 16,
   "accuracy": 40.0,
   "ci": [
    26.3,
    55.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "bonsai2-27b-pq2",
   "profile": "extraction",
   "n": 40,
   "passed": 33,
   "accuracy": 82.5,
   "ci": [
    68.0,
    91.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "bonsai2-27b-ptq1",
   "profile": "extraction",
   "n": 40,
   "passed": 33,
   "accuracy": 82.5,
   "ci": [
    68.0,
    91.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "btl-4-q4km",
   "profile": "extraction",
   "n": 40,
   "passed": 22,
   "accuracy": 55.0,
   "ci": [
    39.8,
    69.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "btl-4",
   "profile": "extraction",
   "n": 40,
   "passed": 25,
   "accuracy": 62.5,
   "ci": [
    47.0,
    75.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "diffusiongemma-26b-mlx",
   "profile": "extraction",
   "n": 40,
   "passed": 31,
   "accuracy": 77.5,
   "ci": [
    62.5,
    87.7
   ],
   "runtime": "mlx",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "edge0-35b",
   "profile": "extraction",
   "n": 40,
   "passed": 21,
   "accuracy": 52.5,
   "ci": [
    37.5,
    67.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "gemma4-12b-midrange",
   "profile": "extraction",
   "n": 40,
   "passed": 39,
   "accuracy": 97.5,
   "ci": [
    87.1,
    99.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "gemma4-12b",
   "profile": "extraction",
   "n": 40,
   "passed": 39,
   "accuracy": 97.5,
   "ci": [
    87.1,
    99.6
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "glm-4.7-flash-q40",
   "profile": "extraction",
   "n": 40,
   "passed": 15,
   "accuracy": 37.5,
   "ci": [
    24.2,
    53.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-3.7b-q4-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 21,
   "accuracy": 52.5,
   "ci": [
    37.5,
    67.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-3.7b-q8-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 20,
   "accuracy": 50.0,
   "ci": [
    35.2,
    64.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-3.7b",
   "profile": "extraction",
   "n": 40,
   "passed": 20,
   "accuracy": 50.0,
   "ci": [
    35.2,
    64.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-a4b-q4",
   "profile": "extraction",
   "n": 19,
   "passed": 15,
   "accuracy": 78.9,
   "ci": [
    56.7,
    91.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-ctx128k-q8",
   "profile": "extraction",
   "n": 40,
   "passed": 26,
   "accuracy": 65.0,
   "ci": [
    49.5,
    77.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-ctx32k",
   "profile": "extraction",
   "n": 40,
   "passed": 26,
   "accuracy": 65.0,
   "ci": [
    49.5,
    77.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-extraction",
   "profile": "extraction",
   "n": 40,
   "passed": 21,
   "accuracy": 52.5,
   "ci": [
    37.5,
    67.1
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-q4_0",
   "profile": "extraction",
   "n": 40,
   "passed": 23,
   "accuracy": 57.5,
   "ci": [
    42.2,
    71.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-q8-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 22,
   "accuracy": 55.0,
   "ci": [
    39.8,
    69.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-vendor-k2",
   "profile": "vendor-k2",
   "n": 40,
   "passed": 31,
   "accuracy": 77.5,
   "ci": [
    62.5,
    87.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-36b-vendor-k2b",
   "profile": "vendor-k2b",
   "n": 40,
   "passed": 33,
   "accuracy": 82.5,
   "ci": [
    68.0,
    91.3
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-4b-bf16-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 20,
   "accuracy": 50.0,
   "ci": [
    35.2,
    64.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-7b-bf16-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 12,
   "accuracy": 30.0,
   "ci": [
    18.1,
    45.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-7b-q4-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 15,
   "accuracy": 37.5,
   "ci": [
    24.2,
    53.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-7b-q8-precision",
   "profile": "extraction",
   "n": 40,
   "passed": 12,
   "accuracy": 30.0,
   "ci": [
    18.1,
    45.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "k2-7b",
   "profile": "extraction",
   "n": 40,
   "passed": 12,
   "accuracy": 30.0,
   "ci": [
    18.1,
    45.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "lfm25-8b-a1b-midrange",
   "profile": "extraction",
   "n": 40,
   "passed": 12,
   "accuracy": 30.0,
   "ci": [
    18.1,
    45.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "minicpm5-2b-exl3",
   "profile": "extraction",
   "n": 40,
   "passed": 15,
   "accuracy": 37.5,
   "ci": [
    24.2,
    53.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "minicpm5-2b-q8-np1",
   "profile": "extraction",
   "n": 40,
   "passed": 23,
   "accuracy": 57.5,
   "ci": [
    42.2,
    71.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "minicpm5-2b",
   "profile": "extraction",
   "n": 40,
   "passed": 15,
   "accuracy": 37.5,
   "ci": [
    24.2,
    53.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "neohorse-1-4b",
   "profile": "extraction",
   "n": 40,
   "passed": 16,
   "accuracy": 40.0,
   "ci": [
    26.3,
    55.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "ornith-1.5-9b",
   "profile": "extraction",
   "n": 40,
   "passed": 25,
   "accuracy": 62.5,
   "ci": [
    47.0,
    75.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "ornith-35b-a3b-q40-recheck",
   "profile": "extraction",
   "n": 40,
   "passed": 34,
   "accuracy": 85.0,
   "ci": [
    70.9,
    92.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "ornith-35b-a3b-q40",
   "profile": "extraction",
   "n": 40,
   "passed": 34,
   "accuracy": 85.0,
   "ci": [
    70.9,
    92.9
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen3-8b-midrange",
   "profile": "extraction",
   "n": 40,
   "passed": 18,
   "accuracy": 45.0,
   "ci": [
    30.7,
    60.2
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen3.5-4b-base",
   "profile": "extraction",
   "n": 40,
   "passed": 16,
   "accuracy": 40.0,
   "ci": [
    26.3,
    55.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen3.8-27b-q4_0",
   "profile": "extraction",
   "n": 40,
   "passed": 32,
   "accuracy": 80.0,
   "ci": [
    65.2,
    89.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen3.8-9b-distill",
   "profile": "extraction",
   "n": 40,
   "passed": 16,
   "accuracy": 40.0,
   "ci": [
    26.3,
    55.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen38-27b-np1",
   "profile": "extraction",
   "n": 40,
   "passed": 31,
   "accuracy": 77.5,
   "ci": [
    62.5,
    87.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen38-27b-q3kxl-chad",
   "profile": "extraction",
   "n": 40,
   "passed": 37,
   "accuracy": 92.5,
   "ci": [
    80.1,
    97.4
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen38-gsqrco-iq3s",
   "profile": "extraction",
   "n": 40,
   "passed": 31,
   "accuracy": 77.5,
   "ci": [
    62.5,
    87.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen38-rebase-b10893",
   "profile": "extraction",
   "n": 40,
   "passed": 31,
   "accuracy": 77.5,
   "ci": [
    62.5,
    87.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "qwen38-vendor-qwen-think",
   "profile": "vendor-qwen-think",
   "n": 40,
   "passed": 31,
   "accuracy": 77.5,
   "ci": [
    62.5,
    87.7
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "reap-60b-20260910",
   "profile": "extraction",
   "n": 40,
   "passed": 19,
   "accuracy": 47.5,
   "ci": [
    32.9,
    62.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "reap-60b-gguf-q4km",
   "profile": "extraction",
   "n": 40,
   "passed": 32,
   "accuracy": 80.0,
   "ci": [
    65.2,
    89.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "reap-60b-mlx-4bit-uniform",
   "profile": "extraction",
   "n": 40,
   "passed": 19,
   "accuracy": 47.5,
   "ci": [
    32.9,
    62.5
   ],
   "runtime": "mlx",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "reap-60b",
   "profile": "extraction",
   "n": 40,
   "passed": 19,
   "accuracy": 47.5,
   "ci": [
    32.9,
    62.5
   ],
   "runtime": "llama.cpp",
   "dataset_id": "d7ae9cbb38fafbe9048baae8b1bc920177b8bbed962237e1da15c38812505408",
   "grader_id": "d511b635ce7bbfd3"
  },
  {
   "suite": "worldview",
   "model": "spark-x25-4b",
   "profile": "extraction",
   "n": 40,
   "passed": 8,
   "accuracy": 20.0,
   "ci": [
    10.5,
    34.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "ternary-bonsai-27b",
   "profile": "extraction",
   "n": 40,
   "passed": 17,
   "accuracy": 42.5,
   "ci": [
    28.5,
    57.8
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  },
  {
   "suite": "worldview",
   "model": "ternary-bonsai-8b",
   "profile": "extraction",
   "n": 40,
   "passed": 15,
   "accuracy": 37.5,
   "ci": [
    24.2,
    53.0
   ],
   "runtime": "llama.cpp",
   "dataset_id": "e97835de9e6fc227447915fb524b8e8059b094d9a411885ecfc2455ea7cc001a",
   "grader_id": "9acfba1b704feb28"
  }
 ]
}