OpenAI GPT-5.5 Launch - FrontierMath Tier 1-3: leaderboard
Metric: Score (%). Source: openai.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 Pro (High) | 52.4 |
| 2 | GPT-5.5 (xHigh) | 51.7 |
| 3 | GPT-5.4 Pro (xHigh) | 50 |
| 4 | GPT-5.4 (xHigh) | 47.6 |
| 5 | Claude Opus 4.7 (xHigh) | 43.8 |
| 6 | Gemini 3.1 Pro | 36.9 |
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-5-launch-frontiermath-tier-1-3 · How It Works · Data refreshed daily, snapshot 2026-09-05.