Suite · screening← Suites
Second-pass screening
Can a second model catch the errors a grounding filter lets through?
- Cases
- 60
- Scored runs
- 76
- Models
- 76
- Top score
- 100.0%
SpecificationMethod · grading · caveat
- Method
- A record and a candidate extraction are shown to a judge model. Some candidates are correct, some are values lifted from the wrong part of the document, some are invented. The judge marks each one accept or reject.
- Grading
- Binary. A case passes when the judge's verdict matches the label.
- Caveat
- This suite is close to saturated. Several models now score above 95 and their confidence intervals overlap, so it no longer separates the top of the field.
- Version
screening/1- Cases
- 60
Recorded runs76 runs · sorted by accuracy
Sorted by accuracy. The bar shows the 95 percent confidence interval. Where intervals overlap, the models are not distinguishable on this suite at this number of cases.
Top of the suite Devstral Small 2 24B 100.0% 95% interval 94.0–100.0
| Model | Score | 95% interval | Passed | Runtime · profile | Recorded |
|---|---|---|---|---|---|
| Devstral Small 2 24Bdevstral-small-2-24b-b10618 | 100.0% | 94.0–100.0 | Passed 60/60 | llama.cppextraction | 2026-08-25 |
| Granite Guardian 4.1 8Bgranite-guardian-4.1-8b | 100.0% | 94.0–100.0overlaps the top interval | Passed 60/60 | llama.cppextraction | 2026-08-31 |
| granite-guardian-gguf-q4km | 100.0% | 94.0–100.0overlaps the top interval | Passed 60/60 | llama.cppextraction | 2026-09-09 |
| K2-Horizon-3.7B (IFM)k2-horizon-3.7b | 100.0% | 94.0–100.0overlaps the top interval | Passed 60/60 | llama.cppextraction | 2026-09-09 |
| qwen3-next-80b-reap-mlx-q4 | 100.0% | 94.0–100.0overlaps the top interval | Passed 60/60 | mlxextraction | 2026-09-08 |
| bonsai2-27b-pq2 | 98.3% | 91.1–99.7overlaps the top interval | Passed 59/60 | llama.cppextraction | 2026-09-18 |
| bonsai2-27b-ptq1 | 98.3% | 91.1–99.7overlaps the top interval | Passed 59/60 | llama.cppextraction | 2026-09-18 |
| Granite 4.2 30Bgranite-4.2-30b-gguf | 98.3% | 91.1–99.7overlaps the top interval | Passed 59/60 | llama.cppextraction | 2026-09-08 |
| granite-guardian-4.1-8b-mlx-bf16 | 98.3% | 91.1–99.7overlaps the top interval | Passed 59/60 | mlxextraction | 2026-09-09 |
| granite-guardian-4.1-8b-mlx-q8 | 98.3% | 91.1–99.7overlaps the top interval | Passed 59/60 | mlxextraction | 2026-09-09 |
| Qwen3-Next-80B-A3B Instruct, REAP prunedqwen3-next-80b-reap | 98.3% | 91.1–99.7overlaps the top interval | Passed 59/60 | llama.cppextraction | 2026-09-08 |
| qwen3-next-80b-reap-mlx-mixed36 | 98.3% | 91.1–99.7overlaps the top interval | Passed 59/60 | mlxextraction | 2026-09-08 |
| Bonsai-27B (Q1_0)bonsai-27b-1bit | 96.7% | 88.6–99.1overlaps the top interval | Passed 58/60 | llama.cppextraction | 2026-09-14 |
| glm-4.7-flash-mlx-q4 | 96.7% | 88.6–99.1overlaps the top interval | Passed 58/60 | mlxextraction | 2026-09-08 |
| glm-4.7-flash-mlx-q8 | 96.7% | 88.6–99.1overlaps the top interval | Passed 58/60 | mlxextraction | 2026-09-08 |
| qwen3-8b-mlx-8bit | 96.7% | 88.6–99.1overlaps the top interval | Passed 58/60 | mlxextraction | 2026-09-08 |
| qwen3-next-80b-mlx-4bit | 96.7% | 88.6–99.1overlaps the top interval | Passed 58/60 | mlxextraction | 2026-09-07 |
| qwen3.5-9b-q8-b10618 | 96.7% | 88.6–99.1overlaps the top interval | Passed 58/60 | llama.cppextraction | 2026-08-25 |
| Qwen3.8-Flash-Nextqwen38-flash-next | 96.7% | 88.6–99.1overlaps the top interval | Passed 58/60 | llama.cppextraction | 2026-09-05 |
| agents-a1-35b-b10618 | 95.0% | 86.3–98.3overlaps the top interval | Passed 57/60 | llama.cppextraction | 2026-08-26 |
| BTL-4 Compact (IQ2_XXS)btl-4 | 95.0% | 86.3–98.3overlaps the top interval | Passed 57/60 | llama.cppextraction | 2026-09-15 |
| flashnext-4.27bpw-m64 | 95.0% | 86.3–98.3overlaps the top interval | Passed 57/60 | llama.cppextraction | 2026-09-08 |
| GLM-4.7-Flashglm-4.7-flash-q8 | 95.0% | 86.3–98.3overlaps the top interval | Passed 57/60 | llama.cppextraction | 2026-08-26 |
| granite-guardian-4.1-8b-mlx-mixed36 | 95.0% | 86.3–98.3overlaps the top interval | Passed 57/60 | mlxextraction | 2026-09-09 |
| Ornith 1.5 35Bornith-1.5-35b-q6-b10618 | 95.0% | 86.3–98.3overlaps the top interval | Passed 57/60 | llama.cppextraction | 2026-08-25 |
| bonsai-27b-mlx2-cortext | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | mlxextraction | 2026-09-14 |
| bonsai-27b-mlx2-m4pro | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | mlxextraction | 2026-09-14 |
| Gemma 4 12Bgemma4-12b | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-08-24 |
| gemma4-12b-b10618 | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-08-25 |
| gemma4-12b-recheck | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-09-17 |
| gemma4-e4b | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-08-24 |
| gemma4-e4b-b10618 | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-08-25 |
| glm-4.7-flash-mlx-mixed_3_6 | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | mlxextraction | 2026-09-08 |
| glm-4.7-flash-mlx-mixed_4_6 | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | mlxextraction | 2026-09-08 |
| minicpm5-2b-exl3 | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-09-17 |
| Nemotron 3.5 Lightning 30Bnemotron-lightning-30b | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-09-05 |
| qwen3.8-27b-mlx-4bit | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | mlxextraction | 2026-09-08 |
| Ternary-Bonsai-27B (prism-ml)ternary-bonsai-27b | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-09-14 |
| ternary-bonsai-27b-recheck | 93.3% | 84.1–97.4overlaps the top interval | Passed 56/60 | llama.cppextraction | 2026-09-17 |
| BTL-4 (Q4_K_M)btl-4-q4km | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-09-15 |
| btl-4-q4km-recheck | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-09-17 |
| Gemma 4 E2Bgemma4-e2b | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-08-24 |
| gemma4-e2b-b10618 | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-08-25 |
| granite-4.2-30b-mlx-q4 | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | mlxextraction | 2026-09-08 |
| qwen3-coder-30b-b10618 | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-08-26 |
| Qwen3-Next-80B-A3B Instructqwen3-next-80b | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-09-05 |
| qwen3-next-80b-a3b-iq4xs | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-08-26 |
| Qwen3-Next-80B-A3B Thinkingqwen3-next-80b-thinking | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-08-27 |
| Qwen3.8-9B-Distill (Q8_0)qwen3.8-9b-distill | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-09-14 |
| qwen3.8-9b-distill-recheck | 91.7% | 81.9–96.4overlaps the top interval | Passed 55/60 | llama.cppextraction | 2026-09-17 |
| k2-36b-ctx32k | 90.0% | 79.9–95.3overlaps the top interval | Passed 54/60 | llama.cppextraction | 2026-09-09 |
| k2-horizon-7b | 90.0% | 79.9–95.3overlaps the top interval | Passed 54/60 | llama.cppextraction | 2026-09-09 |
| mlx-community-Qwen3.6-35B-A3B-4bit | 90.0% | 79.9–95.3overlaps the top interval | Passed 54/60 | mlxextraction | 2026-09-08 |
| nemotron-lightning-30b-mlx-4bit | 90.0% | 79.9–95.3overlaps the top interval | Passed 54/60 | mlxextraction | 2026-09-08 |
| qwen3-next-80b-coder | 90.0% | 79.9–95.3overlaps the top interval | Passed 54/60 | llama.cppextraction | 2026-08-27 |
| edge0-35b | 88.3% | 77.8–94.2overlaps the top interval | Passed 53/60 | llama.cppextraction | 2026-09-16 |
| edge0-35b-recheck | 88.3% | 77.8–94.2overlaps the top interval | Passed 53/60 | llama.cppextraction | 2026-09-17 |
| ornith-1.5-35b-mlx-4bit | 88.3% | 77.8–94.2overlaps the top interval | Passed 53/60 | mlxextraction | 2026-09-08 |
| Qwen3.5 122B-A10Bqwen3.5-122b-a10b-iq3 | 88.3% | 77.8–94.2overlaps the top interval | Passed 53/60 | llama.cppextraction | 2026-08-26 |
| qwen3.6-35b-swiftlm | 88.3% | 77.8–94.2overlaps the top interval | Passed 53/60 | llama.cppextraction | 2026-09-17 |
| Bonsai-8B (Q1_0)bonsai-8b-1bit | 86.7% | 75.8–93.1 | Passed 52/60 | llama.cppextraction | 2026-09-14 |
| Muse-Glimmer 30Bmuse-glimmer-30b | 86.7% | 75.8–93.1 | Passed 52/60 | llama.cppextraction | 2026-09-08 |
| Qwen3.6 35B-A3Bqwen3.6-35b | 86.7% | 75.8–93.1 | Passed 52/60 | llama.cppextraction | 2026-08-27 |
| ternary-bonsai-8b | 86.7% | 75.8–93.1 | Passed 52/60 | llama.cppextraction | 2026-09-17 |
| minicpm5-2b | 85.0% | 73.9–91.9 | Passed 51/60 | llama.cppextraction | 2026-09-15 |
| minicpm5-2b-q8-np1 | 83.3% | 72.0–90.7 | Passed 50/60 | llama.cppextraction | 2026-09-17 |
| LFM 2.5 8B-A1Blfm2.5-8b-a1b | 73.3% | 61.0–82.9 | Passed 44/60 | llama.cppextraction | 2026-08-31 |
| qwen38-27b-q3kxl-chad | 46.7% | 34.6–59.1 | Passed 28/60 | llama.cppextraction | — |
| granite-guardian | 36.7% | 25.6–49.3 | Passed 22/60 | llama.cppextraction | 2026-09-09 |
| granite-guardian-3.1-2b | 0.0% | -0.0–6.0 | Passed 0/60 | llama.cppextraction | 2026-09-07 |
| granite-guardian-mlx-mixed36 | 0.0% | -0.0–6.0 | Passed 0/60 | mlxextraction | — |
| guardian-mixed36-mlxlm | 0.0% | -0.0–6.0 | Passed 0/60 | mlxextraction | — |
| laguna-xs2-mlx-q4 | 0.0% | 0.0–25.9 | Passed 0/11 | mlxextraction | — |
| reapmix36-rapid-mlx | 0.0% | -0.0–6.0 | Passed 0/60 | mlxextraction | — |
| reapq4-mlx_lm | 0.0% | -0.0–6.0 | Passed 0/60 | mlxextraction | — |
| reapq4-rapid-mlx | 0.0% | -0.0–6.0 | Passed 0/60 | mlxextraction | — |
Run log84 logged runs of this suite
Every logged run, newest first (84)
| Finished | Model | Runtime · profile | Score | Coverage | Grader · dataset · config |
|---|---|---|---|---|---|
| bonsai2-27b-ptq1 | not recordedextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 2f2913b42c03fae2 | |
| qwen38-27b-q3kxl-chad | not recordedextraction | 84.8% | Coverage 55% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc e4109198ec0d6a3f | |
| bonsai2-27b-pq2 | not recordedextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 75d8d5feb45c7b60 | |
| qwen3.6-35b-swiftlm | not recordedextraction | 88.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 7d05a9cf37c57f7c | |
| edge0-35b-recheck | not recordedextraction | 88.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc f685f626196f2883 | |
| ternary-bonsai-27b-recheck | not recordedextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc a5afffb46b0e50c4 | |
| qwen3.8-9b-distill-recheck | not recordedextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 4b6dbb06475bbbad | |
| gemma4-12b-recheck | not recordedextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 321d8d33ba14ed0c | |
| btl-4-q4km-recheck | not recordedextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 86e42deccfe15a63 | |
| minicpm5-2b-q8-np1 | not recordedextraction | 83.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 12f2ce70461eb2ba | |
| minicpm5-2b-exl3 | not recordedextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 1564c01170861ff4 | |
| ternary-bonsai-8b | not recordedextraction | 86.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 40d9d3c65e78e666 | |
| edge0-35b | not recordedextraction | 88.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 60a41f7096ed2f0d | |
| minicpm5-2b | not recordedextraction | 85.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 859326c246bacb4d | |
| btl-4-q4km | not recordedextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc df6b9c70d3ecb99c | |
| btl-4 | not recordedextraction | 95.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 8197a1913a41df95 | |
| bonsai-27b-1bit | not recordedextraction | 96.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 06fe499419357acb | |
| bonsai-8b-1bit | not recordedextraction | 86.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 7b113b84e3e9ea89 | |
| bonsai-27b-mlx2-cortext | mlxextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 64e14fdadbcea0e6 | |
| bonsai-27b-mlx2-m4pro | mlxextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 4082207a1256c4b6 | |
| ternary-bonsai-27b | not recordedextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc c5097500538c3719 | |
| qwen3.8-9b-distill | not recordedextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 5ac25f36beb78f8c | |
| k2-36b-ctx32k | not recordedextraction | 90.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc af55e22558068ab0 | |
| k2-horizon-3.7b | not recordedextraction | 100.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 5d3e0bfbb30467e0 | |
| k2-horizon-7b | not recordedextraction | 90.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc e92045e24be569c7 | |
| granite-guardian-4.1-8b-mlx-bf16 | mlxextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 081a28b5708d9572 | |
| granite-guardian-4.1-8b-mlx-q8 | mlxextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 764b495364f3e7ff | |
| granite-guardian | not recordedextraction | 36.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 9de3a458bda36d8c | |
| granite-guardian-4.1-8b-mlx-mixed36 | mlxextraction | 95.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 1e2bab38313786db | |
| guardian-mixed36-mlxlm | mlxextraction | n/a | Coverage 0% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc b56b3c67a8112f7f | |
| granite-guardian | not recordedextraction | 100.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc fe46fd4c1301cd33 | |
| granite-guardian | not recordedextraction | 100.0% | Coverage 41/41 | g 0661b49a10be2d2ad 64c97ca2269c29afc fe46fd4c1301cd33 | |
| granite-guardian-gguf-q4km | not recordedextraction | 100.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 6af9b4aa83361ef8 | |
| granite-guardian | not recordedextraction | 37.3% | Coverage 59/59 | g 0661b49a10be2d2ad 64c97ca2269c29afc 9de3a458bda36d8c | |
| granite-guardian-gguf-q4km | not recordedextraction | 100.0% | Coverage 36/36 | g 0661b49a10be2d2ad 64c97ca2269c29afc 6af9b4aa83361ef8 | |
| granite-guardian | not recordedextraction | 40.0% | Coverage 5/5 | g 0661b49a10be2d2ad 64c97ca2269c29afc 9de3a458bda36d8c | |
| granite-guardian-gguf-q4km | not recordedextraction | 100.0% | Coverage 33/33 | g 0661b49a10be2d2ad 64c97ca2269c29afc 6af9b4aa83361ef8 | |
| granite-guardian-mlx-mixed36 | mlxextraction | n/a | Coverage 0% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc d9be4d5a49d0f4d5 | |
| mlx-community-Qwen3.6-35B-A3B-4bit | mlxextraction | 90.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 4ed45f89d9eca30b | |
| qwen3.8-27b-mlx-4bit | mlxextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 1b2a598c6ef11638 | |
| qwen3-next-80b-reap-mlx-q4 | mlxextraction | 100.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 72e18625ddbdaf10 | |
| qwen3-next-80b-reap-mlx-mixed36 | mlxextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc c37510db6b5ff9cf | |
| reapq4-mlx_lm | mlxextraction | n/a | Coverage 0% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc 2f64770a4290f344 | |
| reapmix36-rapid-mlx | mlxextraction | n/a | Coverage 0% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc 8077358e07c7af36 | |
| reapq4-rapid-mlx | mlxextraction | n/a | Coverage 0% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc ba21b624ebdf49bd | |
| flashnext-4.27bpw-m64 | not recordedextraction | 95.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 028bac48a65abdd9 | |
| qwen3-next-80b-reap | not recordedextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 81efb9eaae394534 | |
| glm-4.7-flash-mlx-mixed_4_6 | mlxextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc c1b73af4ac52ca1f | |
| glm-4.7-flash-mlx-mixed_3_6 | mlxextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 99894ae40745ad56 | |
| muse-glimmer-30b | llama.cppextraction | 86.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 63338a6fdcbdcddd | |
| laguna-xs2-mlx-q4 | mlxextraction | n/a | Coverage 0% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc 3c17fa93e654c0b4 | |
| glm-4.7-flash-mlx-q4 | mlxextraction | 96.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc c80ceb72756eafac | |
| glm-4.7-flash-mlx-q8 | mlxextraction | 96.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc b4008e66dcadf553 | |
| qwen3-8b-mlx-8bit | mlxextraction | 96.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 02039a8c6b78a23b | |
| nemotron-lightning-30b-mlx-4bit | mlxextraction | 90.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 813491de8103980c | |
| granite-4.2-30b-gguf | llama.cppextraction | 98.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 001987450ecbaa8a | |
| ornith-1.5-35b-mlx-4bit | mlxextraction | 88.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 4f3b9812298e963e | |
| granite-4.2-30b-mlx-q4 | mlxextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc f71ccbbb16cd8099 | |
| qwen3-next-80b-mlx-4bit | mlxextraction | 96.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 22413c6aa05bedb0 | |
| granite-guardian-3.1-2b | llama.cppextraction | 0.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc c3bc4d1194d50b4b | |
| qwen38-flash-next | llama.cppextraction | 96.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc dd9b4d06d5abee09 | |
| nemotron-lightning-30b | llama.cppextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc bd58c270aedc9f3d | |
| qwen3-next-80b | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc ede1a2072fbaea6c | |
| granite-guardian-4.1-8b | llama.cppextraction | 100.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 9ba7cd65a17e6418 | |
| lfm2.5-8b-a1b | llama.cppextraction | 73.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 2cbf094131c24516 | |
| qwen3-next-80b-coder | llama.cppextraction | 90.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc e7b3303ff47f6803 | |
| qwen3.6-35b | llama.cppextraction | 86.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 4246ff56e771b097 | |
| qwen3-next-80b-thinking | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 4320932025e05e5d | |
| qwen3-next-80b | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc ede1a2072fbaea6c | |
| qwen3-next-80b-a3b-iq4xs | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc c6cb8e26e5eec1ec | |
| glm-4.7-flash-q8 | llama.cppextraction | 95.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc b7d076058290ae5f | |
| glm-4.7-flash-q8 | llama.cppextraction | n/a | Coverage 0% coverage | g 0661b49a10be2d2ad 64c97ca2269c29afc b7d076058290ae5f | |
| qwen3.5-122b-a10b-iq3 | llama.cppextraction | 88.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 45dab17de7814804 | |
| agents-a1-35b-b10618 | llama.cppextraction | 95.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc fe6603a03488c606 | |
| qwen3-coder-30b-b10618 | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 01f8fd00f78cb299 | |
| qwen3.5-9b-q8-b10618 | llama.cppextraction | 96.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 6c6da4df0333507c | |
| gemma4-12b-b10618 | llama.cppextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 79323c88f8e515df | |
| gemma4-e2b-b10618 | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 80f542cbf88cfba7 | |
| gemma4-e4b-b10618 | llama.cppextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc b75251f174426f4d | |
| ornith-1.5-35b-q6-b10618 | llama.cppextraction | 95.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc ce44f5f606a0131e | |
| devstral-small-2-24b-b10618 | llama.cppextraction | 100.0% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc d8a2ef703d82163d | |
| gemma4-12b | llama.cppextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc b7d605769821c0d8 | |
| gemma4-e4b | llama.cppextraction | 93.3% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 824bef7dab174615 | |
| gemma4-e2b | llama.cppextraction | 91.7% | Coverage 60/60 | g 0661b49a10be2d2ad 64c97ca2269c29afc 905fc96bd8c3e874 |