742b2ad1d7ee115c26e1687d3377581455a4fa69
Same 9 cases as the retrieval eval, so the numbers compare directly: hand-written keywords hit 8 of 8, this is what the model reaches on its own. Reports the hand-written query next to the model's for every case, because where the phrasing differs is the useful part. Opt-in on MAVEN_KIWIX_URL + MAVEN_LLM_URL, like the other evals. Result on Qwen3.5-0.8B: 3 of 8, identical on all three runs. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
Description
No description provided
Languages
Go
97.1%
HTML
0.9%
Shell
0.6%
CSS
0.5%
Makefile
0.3%
Other
0.6%