agent evals / brisk-kestrel

Qwen/Qwen3.6-35B-A3B-FP8

releasepass ratetrialsfinished
acp-eval-quick 100.0% 3 58d ago

per-task — acp-eval-quick

taskpass rate
00-smoke 100.0%
04-multi-step-state 100.0%
09-fix-cli-bug 100.0%