OpenAI GPT-5.5 Launch - Humanity's Last Exam (no tools) — leaderboard
Metric: Score (%). Source: openai.com. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 46.9 |
| 2 | Gemini 3.1 Pro (Preview) | 44.4 |
| 3 | GPT-5.5 Pro | 43.1 |
| 4 | GPT-5.4 Pro (xHigh) | 42.7 |
| 5 | GPT-5.5 | 41.4 |
| 6 | GPT-5.4 | 39.8 |
Interactive version: theaggregate.ai/benchmark?slug=openai-gpt-5-5-launch-humanity-s-last-exam-no-tools · How the rankings work · Data refreshed daily, snapshot 2026-07-22.