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

Model · measured only← Models

reap-60b-gguf-q4km

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

Scored runs
5
Run log entries
5
RecordIdentifier

reap-60b-gguf-q4km

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
synthesis81.7%70.1–89.4Passed 49/60llama.cppextraction2026-09-10
toolcall41.7%30.1–54.3Passed 25/60llama.cppextraction2026-09-10
toolscale87.5%73.9–94.5Passed 35/40llama.cppextraction2026-09-10
worldview80.0%65.2–89.5Passed 32/40llama.cppextraction2026-09-10
VOID-degenerate-nullschemaflagged100.0%94.9–100.0Passed 72/72llama.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 recordedextraction81.7%Coverage 60/60g 4156dd3c13361e8bd 267d1954e225c5b6c 5d5c05e03d9c61e2
VOID-degenerate-nullschemanullschema/1not recordedextraction100.0%Coverage 72/72g d7448e0f5fc3f9afd 3b91280bb40372efc b923bc8484d5f158
worldviewworldview/2not recordedextraction80.0%Coverage 40/40g 9acfba1b704feb28d e97835de9e6fc227c 361b96fbc9be289c
toolscaletoolscale/1not recordedextraction87.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c 437c75c01b4063cd
toolcalltoolcall/1not recordedextraction41.7%Coverage 60/60g 804e8fc9457649d8d 10af88c170513155c 4faf8950bd5037a5