Tim(@TimGMath):The latest versions of ArXivMath and BrokenArXiv have been released! GPT 5.6 Sol takes top spot on ArXivMath, while GPT 5.5 barely manages to stay on top on BrokenArXiv. Fable 5 is the strongest non-GPT model, reaching second place on ArXivMath and third place on BrokenArXiv.

Tim

@TimGMath

Mathematician at ETH Zurich, interested in arithmetic geometry and artificial intelligence

가입 April 2026

6 팔로잉 중 109 팬

Tim@TimGMath

2026.07.16 18:34

The latest versions of ArXivMath and BrokenArXiv have been released! GPT 5.6 Sol takes top spot on ArXivMath, while GPT 5.5 barely manages to stay on top on BrokenArXiv. Fable 5 is the strongest non-GPT model, reaching second place on ArXivMath and third place on BrokenArXiv.