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

Model · measured only← Models

qwen-agentworld-35b

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

Scored runs
3
Run log entries
4
RecordIdentifier

qwen-agentworld-35b

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
chainwalk50.0%9.5–90.5Passed 1/2llama.cppextraction2026-09-07
tools80.0%54.8–93.0Passed 12/15llama.cppextraction2026-09-07
toolscale72.5%57.2–83.9Passed 29/40llama.cppextraction2026-09-07

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
chainwalkchainwalk/3llama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c c4305e58879e2b40
chainwalkchainwalk/3llama.cppextraction50.0%Coverage 2/2g f4bfcf6f040b0978d 129a9e74408c8919c c4305e58879e2b40
toolscaletoolscale/1llama.cppextraction72.5%Coverage 40/40g a2bc3751abfa28e0d b24abb108c409178c edcc1fd1f9bd35f0
toolstools/1llama.cppextraction80.0%Coverage 15/15g 2763675a5c3da564d 33a44812f0ad4c39c e56fd9e9b9103b0a