How good are frontier models at physics?

arxiv.org
September 16, 2026
2 min read
50/100
Summary
Computer Science > Artificial Intelligence [Submitted on 11 Sep 2026] Title:How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks View PDF HTML (experimental)Abstract:Low reported scores on leading physics benchmarks, including those featured in the Artificial Analysis Intelligence Index (2026), suggest that frontier languag...
Coverage & discussions
Hacker News Β· arxiv.org
Community discussions
Historical count: 4 Β· 4 saved in sample Β· Historical sample
Awaiting analysis