zcbot/evaluation/datasets
caoqianming cee4eb4c14 feat(eval): add reproducible technical benchmark 2026-08-03 16:10:38 +08:00
..
materials_core.json feat(eval): add reproducible technical benchmark 2026-08-03 16:10:38 +08:00
production_full_safe.json feat(eval): add reproducible technical benchmark 2026-08-03 16:10:38 +08:00
production_smoke.json feat(eval): add reproducible technical benchmark 2026-08-03 16:10:38 +08:00
smoke.json feat(eval): add reproducible technical benchmark 2026-08-03 16:10:38 +08:00