Spaces:

Nomearod
/

agentbench

Sleeping

App Files Files Community

agentbench / agent_bench /evaluation /rubrics

Commit History

rubric: clarify groundedness reference scope (snippets-only) for v1.1 gold (#20)

e16544c
unverified

Jane Yeung Claude Opus 4.7 (1M context) commited on May 5

feat(judges): CitationFaithfulnessJudge with all-or-nothing aggregation

04d9ea0

Nomearod Claude Opus 4.7 (1M context) commited on May 4

feat(judges): CompletenessJudge + three-point reference-based rubric

80be2d8

Nomearod Claude Opus 4.7 (1M context) commited on May 4

feat(judges): RelevanceJudge + anchored three-point rubric

b170eb6

Nomearod Claude Opus 4.7 (1M context) commited on May 4

feat(judges): GroundednessJudge + anchored binary rubric

30a5e0c

Nomearod Claude Opus 4.7 (1M context) commited on May 4