Back to Benchmarks
ðŸ§
HLE
Humanity's Last Exam
2500 expert-vetted questions across mathematics, sciences, humanities
🧠Knowledge & Reasoning
Best: 57.9%
10 Models Evaluated
Champion
Claude Opus 4.8
Anthropic
57.9%
Best Score
Model Rankings
All models ranked by score on HLE. Scores are relative to the best score of 57.9%.
| # | Model | Provider | Score | vs Best |
|---|---|---|---|---|
| 1 | Claude Opus 4.8 | Anthropic | 57.9% | Best |
| 2 | Claude Opus 4.7 Elo 1500 | Anthropic | 54.7% | -3.2% |
| 3 | Claude Opus 4.6 Elo 1503 | Anthropic | 53% | -4.9% |
| 4 | GLM-5 Elo 1454 | Zhipu AI | 50.4% | -7.5% |
| 5 | Claude Sonnet 4.6 Elo 1460 | Anthropic | 49% | -8.9% |
| 6 | Gemini 3.1 Pro Elo 1492 | 45.8% | -12.1% | |
| 7 | Gemini 3 Pro Elo 1486 | 45.8% | -12.1% | |
| 8 | GPT-5.4 Pro Elo 1480 | OpenAI | 43.1% | -14.8% |
| 9 | DeepSeek V4 Pro (Max) | DeepSeek | 37.7% | -20.2% |
| 10 | Qwen 3.5 Elo 1450 | Alibaba | 28.7% | -29.2% |
Score Distribution
Claude Opus 4.8
57.9%
Claude Opus 4.7
54.7%
Claude Opus 4.6
53%
GLM-5
50.4%
Claude Sonnet 4.6
49%
Gemini 3.1 Pro
45.8%
Gemini 3 Pro
45.8%
GPT-5.4 Pro
43.1%
DeepSeek V4 Pro (Max)
37.7%
Qwen 3.5
28.7%
Run This Benchmark
Learn how to evaluate your own models on HLE.
HLE is a standardized benchmark for evaluating AI model capabilities.
To run this benchmark on your own models, visit the official benchmark page or leaderboard for detailed instructions, code, and evaluation scripts.
Data compiled from official model cards, public leaderboards, and independent evaluations.