Advanced math
FrontierMathTier 1–3
Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better.
Rankings
Higher is betterFrontierMath — frequently asked questions
- What is FrontierMath?
- Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better.
- Which AI model scores highest on FrontierMath?
- GPT-5.5-Pro by OpenAI holds the best FrontierMath (Tier 1–3) result among tracked models, at 52.4% (released Apr 23 2026). Higher scores are better on this benchmark.
- What are the top 5 models on FrontierMath?
- 1. GPT-5.5-Pro (OpenAI) — 52.4%; 2. GPT-5.5 (OpenAI) — 51.7%; 3. GPT-5.4-Pro (OpenAI) — 50%; 4. GPT-5.4 (OpenAI) — 47.6%; 5. Claude Opus 4.7 (Anthropic) — 43.8%.
- How many models have a published FrontierMath score?
- 6 tracked models have a published FrontierMath (Tier 1–3) score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.