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

Model · measured only← Models

ornith-9b-kvq4

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

Scored runs
3
Run log entries
3
RecordIdentifier

ornith-9b-kvq4

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

Recorded runs3 scored · 95% intervals
SuiteScore95% interval PassedRuntime · profileRecorded
grounding80.0%72.1–86.1Passed 100/125llama.cppextraction2026-09-12
nullschema56.9%45.4–67.7Passed 41/72llama.cppextraction2026-09-12
toolcall100.0%94.0–100.0Passed 60/60llama.cppextraction2026-09-12

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 (3)
FinishedSuiteRuntime · profileScoreCoverageGrader · dataset · config
toolcalltoolcall/1not recordedextraction100.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 970506005273665a
groundinggrounding/1not recordedextraction80.0%Coverage 125/125g 30b933dcc6a7e2d4d dcb396faf8b83b0ac 4c61ed44aed10e7a
nullschemanullschema/1not recordedextraction56.9%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc 32a57cca965b6777