Metraipolis › archive › dc_ce92efef3e9e
How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks — arXiv:2609.13009
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13009
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:02:59.136Z
- SHA-256 of the archived text
9e4dd487ddb378f1bdc347b5a8726ee8e3efbb7a6eb18108b2c3c24b59bf0662- Stable URL of this page
https://metraipolis.com/documento/dc_ce92efef3e9e
How to cite
How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks — arXiv:2609.13009 — arXiv (en), https://arxiv.org/abs/2609.13009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce92efef3e9e (Metraipolis archive dc_ce92efef3e9e, sha256 9e4dd487ddb378f1bdc347b5a8726ee8e3efbb7a6eb18108b2c3c24b59bf0662)
BibTeX
@misc{dcce92efef3e9e,
title = {How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks — arXiv:2609.13009},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13009},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce92efef3e9e; sha256 9e4dd487ddb378f1bdc347b5a8726ee8e3efbb7a6eb18108b2c3c24b59bf0662},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Low reported scores on leading physics benchmarks, including those featured in the Artificial Analysis Intelligence Index (2026), suggest that frontier language models still struggle with advanced physics, a demanding test of their scientific reasoning and quantitative problem-solving abilities. Yet this impression does not always align with domain experts' experiences using these models in their work. We revisit these reported findings by evaluating frontier models on six widely used physics benchmarks and auditing them with experts, focusing on text-only problems with verifiable final answers. For each subfield of physics, faculty and graduate researchers with relevant expertise carefully review problem statements, reference solutions, and model responses to distinguish genuine model errors from grader errors, incorrect reference solutions, and ambiguous or underspecified questions. Most audited cases initially evaluated as incorrect reflect these benchmarking issues rather than errors in the models' physics reasoning. We then ask experts to address these benchmarking issues by correcting erroneous reference solutions and repairing or excluding flawed questions. We find that GPT-5.6-Sol's measured mean@4 rises from 47.3% to 78.7% on HLE-Physics and from 61.0% to 87.2% on CMT-Benchmark, while its corrected pass@4 reaches 94.4% on the 54 retained CritPt challenges. Corrected scores are computed on the retained evaluation subsets following expert review. Scores on the audited subsets of UGPhysics, PRISM-Physics, and PHYBench also rise substantially after correction. These findings suggest that current benchmarks substantially understate frontier models' ability to solve well-posed physics problems. Near-saturation on these closed-ended tasks highlights the need for more demanding, expert-validated evaluations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.13009 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T02:51:27.829Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).