Humanity's Last Exam (Anthropic No Tools) — leaderboard
Metric: Accuracy (%). Source: www-cdn.anthropic.com. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 49.8 |
| 2 | Claude Opus 4.7 | 46.9 |
| 3 | Gemini 3.1 Pro (Preview) | 44.4 |
| 4 | GPT-5.5 | 41.4 |
Interactive version: theaggregate.ai/benchmark?slug=humanity-s-last-exam-anthropic-no-tools · How the rankings work · Data refreshed daily, snapshot 2026-07-22.