FrontierMath Tier 1-3 (v2)
Can the model solve difficult problems that require more than factual recall?
Reasoning7 ranked models7 reported values1 reportsHigher is better
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | GPT-5.6 SolOpenAI | 89.0% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 2 | Claude Fable 5Anthropic | 87.0% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 3 | GPT-5.5OpenAI | 85.3% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 4 | GPT-5.6 TerraOpenAI | 84.9% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 5 | Claude Opus 4.8Anthropic | 80.0% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 6 | GPT-5.6 LunaOpenAI | 78.6% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
| 7 | Gemini 3.1 Pro PreviewGoogle | 59.6% | Reported configurationOpenAI report1 value · 1 reportJul 9, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology
Can the model solve difficult problems that require more than factual recall?
Multi-step reasoning on academic, mathematical, or abstract problems. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
Method / source