Humanity's Last Examno tools

Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better.

Claude Fable 5.1 by Anthropic holds the best Humanity's Last Exam (no tools) result among tracked models, at 60.9% (released Sep 1 2026). Higher scores are better on this benchmark.

1. Claude Fable 5.1 (Anthropic) — 60.9%; 2. Claude Opus 5 (Anthropic) — 56.3%; 3. Claude Opus 4.8 (Anthropic) — 49.8%; 4. Claude Opus 4.7 (Anthropic) — 46.9%; 5. Gemini 3.1 Pro (Google) — 44.4%.

22 tracked models have a published Humanity's Last Exam (no tools) score. Scores are collected from published lab reports and benchmark sources, with recorded sources credited alongside the results. We do not re-run the evaluations.

DeepSeek-V4-Pro-0813 by DeepSeek is the highest-ranked model with downloadable weights on Humanity's Last Exam (no tools), scoring 42.7% at rank 8 overall.