agentbench / agent_bench /evaluation /datasets /tech_docs_golden.json

Commit History

feat(goldens): add source_snippets to 8 FastAPI calibration items
a48afb9

Nomearod Claude Opus 4.7 (1M context) commited on

fix: grounded refusal checks no-sources, reference_answer for judge, mock disclaimer
520796c

Nomearod Claude Opus 4.6 (1M context) commited on

feat: Day 7 β€” evaluation harness, metrics, report, expanded golden dataset
c378584

Nomearod Claude Opus 4.6 (1M context) commited on

feat: Day 4 β€” corpus, ingest script, first 10 golden questions
a152b95

Nomearod Claude Opus 4.6 (1M context) commited on