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

Model · measured only← Models

diffusiongemma-26b-mlx

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

Scored runs
4
Run log entries
4
RecordIdentifier

diffusiongemma-26b-mlx

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

Recorded runs4 scored · 95% intervals
SuiteScore95% interval PassedRuntime · profileRecorded
synthesis80.0%68.2–88.2Passed 48/60mlxextraction2026-09-11
toolcall5.0%1.7–13.7Passed 3/60mlxextraction2026-09-11
toolscale100.0%91.2–100.0Passed 40/40mlxextraction2026-09-11
worldview77.5%62.5–87.7Passed 31/40mlxextraction2026-09-11

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 (4)
FinishedSuiteRuntime · profileScoreCoverageGrader · dataset · config
synthesissynthesis/2mlxextraction80.0%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 6220b53efc9f35b4
worldviewworldview/2mlxextraction77.5%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c b0b19b278db1058f
toolscaletoolscale/1mlxextraction100.0%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 40a7e393e161d98f
toolcalltoolcall/1mlxextraction5.0%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 49640f29f7104a95