Skip to content

FrontierMath: hard maths problems solved

Best score on Epoch AI's FrontierMath (corrected v2 set), plotted at each model's release date.

Topics: Mathematics, Benchmarks

What this measures: Hundreds of unpublished problems written by mathematicians. Tiers 1–3 are advanced; Tier 4 is research-level. Answers are checked automatically.

  • Tiers 1–3 (advanced)
  • Tier 4 (research-level)
0%50%100%20252026

Tier 4 (research-level), Saturated: Epoch AI considers Tier 4 saturated: GPT-6 Astra solved the last problem no model had solved (September 2026), and GPT-6.1 Sol and Claude Fable 5.2 both score 100%. Now watch: FrontierMath Erdős (68 genuinely open problems).

Epoch AI re-ran older models on the corrected v2 problem set (June 2026), so early points come from those re-runs. OpenAI funded FrontierMath and has access to many problems; Epoch keeps a held-out set. These are not proofs of open problems.

Source: Epoch AIData as of 10 Nov 2026
Show data table and sources
SeriesDateLabelValue
Tiers 1–3 (advanced)17 Dec 2024o1 (high)15%
Tiers 1–3 (advanced)31 Jan 2025o3-mini (high)19%
Tiers 1–3 (advanced)16 Apr 2025o4-mini (high)36%
Tiers 1–3 (advanced)7 Aug 2025GPT-5 (high)55%
Tiers 1–3 (advanced)11 Dec 2025GPT-5.2 Pro74%
Tiers 1–3 (advanced)5 Mar 2026GPT-5.4 Pro83%
Tiers 1–3 (advanced)23 Apr 2026GPT-5.5 Pro88%
Tiers 1–3 (advanced)9 Jul 2026GPT-5.6 Sol89%
Tiers 1–3 (advanced)1 Sept 2026Claude Fable 5.190%
Tiers 1–3 (advanced)3 Sept 2026GPT-6 Astra94%
Tiers 1–3 (advanced)9 Nov 2026Claude Fable 5.2 (max)95%
Tier 4 (research-level)16 Apr 2025o4-mini4.9%
Tier 4 (research-level)7 Aug 2025GPT-522%
Tier 4 (research-level)11 Dec 2025GPT-5.2 Pro46%
Tier 4 (research-level)5 Mar 2026GPT-5.4 Pro59%
Tier 4 (research-level)23 Apr 2026GPT-5.5 Pro78%
Tier 4 (research-level)9 Jun 2026Claude Fable 590%
Tier 4 (research-level)3 Sept 2026GPT-6 Astra98%
Tier 4 (research-level)29 Sept 2026GPT-6.1 Sol (max)100%
Tier 4 (research-level)9 Nov 2026Claude Fable 5.2 (max)100%

Entries with this chart