OpenAI GPT-5.5 Launch - FrontierMath Tier 1-3: leaderboard
The "FrontierMath Tier 1-3" subtask of OpenAI GPT-5.5 Launch. A benchmark result reported in the OpenAI GPT-5.5 launch announcement, as self-reported by the model developer.
Metric: Score (%). Source: openai.com. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 Pro (High) | 52.4 | #17 (GPT-5.5 Pro) |
| 2 | GPT-5.5 (xHigh) | 51.7 | #31 (GPT-5.5) |
| 3 | GPT-5.4 Pro (xHigh) | 50 | #32 (GPT-5.4 Pro) |
| 4 | GPT-5.4 (xHigh) | 47.6 | #79 (GPT-5.4) |
| 5 | Claude Opus 4.7 (xHigh) | 43.8 | #49 (Claude Opus 4.7) |
| 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 2026-10-20.