FrontierMath - Tiers 1-3 — leaderboard

Metric: Accuracy (%, 290 problems). Source: epoch.ai. 100 models tracked.

Top models

#ModelScore
1GPT-5.5 (xHigh)51.7
2GPT-5.5 Pro (xHigh)51
3GPT-5.4 Pro (xHigh)50
4GPT-5.4 (xHigh)47.6
5Claude Opus 4.8 (Max)47.24
6Claude Opus 4.7 (xHigh)43.79
7GPT-5.2 (xHigh)40.7
8Claude Opus 4.6 (Max)40.7
9GPT-5.2 (High)40.34
10Claude Opus 4.6 (Thinking 32K)40
11Muse Spark39
12Kimi K2.638.97
13Gemini 3.5 Flash (High)38.97
14Claude Opus 4.6 (Non-reasoning)38.28
15Gemini 3 Pro (Preview)37.6

Interactive version: theaggregate.ai/benchmark?slug=frontiermath-tiers-1-3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.