Humanity's Last Exam (Anthropic Tools): leaderboard
Anthropic system-card run of Humanitys Last Exam with tools, covering expert-level academic reasoning across many domains.
Metric: Accuracy (%). Source: www-cdn.anthropic.com. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 57.9 | #37 |
| 2 | Claude Opus 4.7 | 54.7 | #49 |
| 3 | GPT-5.5 | 52.2 | #31 |
| 4 | Gemini 3.1 Pro | 51.4 |
Interactive version: theaggregate.ai/benchmark?slug=humanity-s-last-exam-anthropic-tools · How It Works · Data refreshed daily, snapshot 2026-10-20.