Benchmark

FRAMES

Factuality, Retrieval, And reasoning MEasurement Set - a unified evaluation dataset of 824 challenging multi-hop questions for testing retrieval-augmented…

Modality
text
Categories
reasoning, search
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
DeepSeek-V3DeepSeek0.7332024-12-25evidence
Kimi K2-Thinking-0905Moonshot AI0.872025-09-05evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.