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

Model · measured only← Models

qwen3.8-iq1s

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

Scored runs
5
Run log entries
5
RecordIdentifier

qwen3.8-iq1s

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
chainwalk0.0%0.0–65.8Passed 0/2llama.cppagentic-fast2026-08-24
enrichment48.1%35.4–61.1Passed 26/54llama.cppstudy-nothink—
epistemics56.2%42.3–69.3Passed 27/48llama.cppstudy-nothink—
tagger14.0%9.0–21.0Passed 18/129llama.cppstudy-nothink—
tools66.7%41.7–84.8Passed 10/15llama.cppagentic-fast—

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
taggertagger/2llama.cppstudy-nothink31.6%Coverage 44.2% coverageg 956e03bbffa79aa4d 7ef587bf33e5788ac f6700e17f70a9c2a
epistemicsepistemics/4llama.cppstudy-nothink77.1%Coverage 72.9% coverageg 2a2f7e4e90d6dd63d 4bce453fd376553cc 4bfecdedff811923
toolstools/1llama.cppagentic-fast76.9%Coverage 86.7% coverageg d6a32c09e57bea7bd 33a44812f0ad4c39c 02e356bf0012eaf2
enrichmentenrichment/3llama.cppstudy-nothink60.5%Coverage 79.6% coverageg 7d661b93852b5ffdd 75361864baa727abc 11d22e9108889bce
chainwalkchainwalk/3llama.cppagentic-fast0.0%Coverage 2/2g d31d3c4c6285617fd 129a9e74408c8919c e2e5d225bbfe60d6