Epoch AI audits 15 benchmarks; Anthropic says 40% of Critical Point physics questions are broken
Jsevillamol · x · 2026-09-19
- Epoch AI launched Benchmark Reviews, auditing 15 AI benchmarks in its first batch: 4 Verified, 9 Flawed, and 2 with insufficient information to review.
- Researcher Michelle Campeau explained that a model can look 40% better overnight simply because the benchmark changed, not the model. Anthropic's latest system card admitted over 40% of Critical Point physics benchmark questions are broken, so they ran a privately corrected version — making scores incomparable to past results.
- Her caution: comparing across corrected versions invites the wrong takeaway that scores jumped 40%, when benchmark quality itself is the weak link.
Related event: Epoch AI's First Benchmark Audit Flags 9 of 15 as Flawed(22 posts)→
More from Models
- Musk cites unsustainable Grok Bot costs as Hermes offers one-command agent migration — Teknium · 2026-11-04
- Hobbyist rewrites Qwen 0.6B weights with 39.8M tokens, no gradients, in 3h12m — Altruistic_Heat_9531 · 2026-11-04
- Same leak, reshared: ChatGPT's five family plan prices spotted again — heyshrutimishra · 2026-11-04
- KOL visits StepFun's Shanghai office, hints a powerful new model is coming — teortaxesTex · 2026-11-04
- Fable 5.5 delayed as Anthropic reportedly bets OpenAI's Astra 6.2 won't beat it — haider1 · 2026-11-04
- ByteDance open-sources Axion 1.0-35B agent foundation model with full reproducible recipe — pmttyji · 2026-11-04