工具IMAGE
Epoch AI launches Benchmark Reviews audit program
Epoch AI has launched Benchmark Reviews, auditing 15 AI benchmarks in its first round: 4 verified, 9 flawed, and 2 with too little information to review.
Epoch AI
@EpochAIResearchArchived 2026.09.18Originally posted 2026.09.18
Epoch AI @EpochAIResearchOriginally posted 2026.09.18
Introducing Benchmark Reviews: our new initiative to audit AI benchmarks. We are launching with 15 benchmarks: 4 Verified, 9 Flawed, and 2 with not enough information for a review. https://t.co/xU43tv32gH
x.com/epochairesearch/status/2100704765332394255Archived 2026.09.18 10:22