Humanity's Last Exam Leaderboard
2,500 expert-level questions spanning mathematics, sciences, and humanities. Designed to be 'the final closed-ended academic evaluation' that even top models fail most of.
Why it matters: The hardest academic benchmark — top models still fail 60-65% of questions. Shows how far we are from genuine expert-level reasoning.
Top Model
59%
Claude Fable 5
Average Score
24.5%
Across 32 models
Models Tested
32
Metric: accuracy
Human Baseline
-
Score Range: 0%–100%
HLE Scores - Top 25 Models
Ranked by HLE score (%)
Model Rankings
All models with a reported HLE score, ranked by highest accuracy.
About HLE
- Full Name
- Humanity's Last Exam
- Category
- Reasoning
- Metric
- accuracy (%)
- Score Range
- 0%–100%
- Human Baseline
- Not established
- Status
- Active
HLE is a standardized evaluation that measures AI model performance on specific tasks. It provides comparable scores across different models, helping developers choose the right model for their needs.
Claude Fable 5 currently holds the top score on the HLE benchmark. See our full rankings table above for the complete leaderboard with 32 models.
We update benchmark data from multiple sources including HuggingFace open-source model leaderboards and LMArena. Scores are refreshed regularly as new evaluations are published and new models are released.
No. While HLE is an important indicator, real-world performance depends on many factors including pricing, latency, context window, and specific task requirements. We recommend using our composite score which weighs multiple benchmarks and practical factors.