FreshContextA context lab · Fife
Drawing
02 · Benchmarks
Sheet
2 of 3
Rev
A · 2026-10-01

Model · measured only← Models

qwen38-27b-np1

5 recorded runs. This model has no written entry yet.

Scored runs
5
Run log entries
5
RecordIdentifier

qwen38-27b-np1

Every result below is as recorded. Without a written entry there is no stated reason for the test and no verdict.

Recorded runs5 scored · 95% intervals
SuiteScore95% interval PassedRuntime · profileRecorded
nullschema76.4%65.4–84.7Passed 55/72llama.cppextraction2026-09-10
synthesis83.3%72.0–90.7Passed 50/60llama.cppextraction2026-09-10
toolcall100.0%94.0–100.0Passed 60/60llama.cppextraction2026-09-10
toolscale100.0%91.2–100.0Passed 40/40llama.cppextraction2026-09-10
worldview77.5%62.5–87.7Passed 31/40llama.cppextraction2026-09-10

Runs marked unenforced were measured through mlx_lm on a suite that requires constrained decoding. mlx_lm accepts the schema and ignores it, so those numbers do not measure what the suite is designed to measure. They are kept and labelled rather than deleted.

Every run log entry for this model (5)
FinishedSuiteRuntime · profileScoreCoverageGrader · dataset · config
synthesissynthesis/2not recordedextraction83.3%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 2867e80b35de0e49
nullschemanullschema/1not recordedextraction76.4%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 458eb55eee2cc3a3
worldviewworldview/2not recordedextraction77.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c cf60f4eb1ae532f8
toolscaletoolscale/1not recordedextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 2b5ec5e83a2c8961
toolcalltoolcall/1not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 7019f408382de810