FrontierMathTier 4 (v2)

The rebuilt edition of FrontierMath's hardest tier — research-level maths of the kind professional mathematicians work on. It is a different question set from the first Tier 4, and scores on it run far higher, so read the two as separate tests rather than progress. Higher is better.

GPT-6 Astra by OpenAI holds the best FrontierMath (Tier 4 (v2)) result among tracked models, at 97.6% (released Sep 3 2026). Higher scores are better on this benchmark.

1. GPT-6 Astra (OpenAI) — 97.6%.

1 tracked model has a published FrontierMath (Tier 4 (v2)) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.