How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2609.13009/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTHow Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks — HN submissionhttps://news.ycombinator.com/item?id=49731620urn:hackerpapers:submission:2609.13009:49731620Wed, 16 Sep 2026 19:19:08 GMT<p>How good are frontier models at physics?</p><p></p><p>100 points; 50 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2609.13009/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AIHow Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks — HN submissionhttps://news.ycombinator.com/item?id=49693488urn:hackerpapers:submission:2609.13009:49693488Mon, 14 Sep 2026 08:07:07 GMT<p>How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken</p><p></p><p>4 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2609.13009/">Paper and source history</a>. A submission is not an endorsement.</p>cs.AI