48%
best score so far on FrontierMath Tier 4, the hardest of these 8 maths benchmarks for AI
What the chart shows
Each row is one maths benchmark in Epoch AI’s hub. The best score so far is highest on FrontierMath Tier 4 (v2) (100%, GPT-6.1 Sol (max), 2026) and lowest on FrontierMath Tier 4 (48%, AI co-mathematician, 2026).
FrontierMath Tier 4 (v2), OTIS Mock AIME, IMO-ProofBench, MATH Level 5, GSM8K and FrontierMath Tiers 1-3 (v2) are at 90% or more, close to their ceiling, so they no longer separate the leading models. Newer benchmarks are built to stay hard, which is why their scores start low.
Benchmarks with their own chart pages: FrontierMath Tier 4.
Key numbers
| Measure | Value |
|---|---|
| FrontierMath Tier 4 (v2) (2026) | 100% |
| OTIS Mock AIME (2026) | 100% |
| IMO-ProofBench (2026) | 100% |
| MATH Level 5 (2025) | 98% |
| GSM8K (2024) | 94% |
| FrontierMath Tiers 1-3 (v2) (2026) | 94% |
| FrontierMath Tiers 1-3 (2026) | 52% |
| FrontierMath Tier 4 (2026) | 48% |
How to read it
- Each cell is the best score among models released that year, from Epoch AI’s own runs or the results it collects; settings differ by benchmark.
- Only benchmarks scored as a share of questions or tasks, with results from at least two release years, are included.
- Choose a benchmark from the list above the chart; the full grid is in the downloadable image and CSV.
Source: Epoch AI, 2026: Benchmarking Hub, read 3 November 2026. Chart and text by AI Adoption.
Numbers checked against the published data on 3 November 2026.
Download the data (CSV) · Cite this chart
Numbers checked against the published data on 3 November 2026.
Download the data (CSV) · Cite this chart
Discussion