HLE-Verified
Progress Over Time
Interactive timeline showing model performance evolution on HLE-Verified
State-of-the-art frontier
Open
Proprietary
HLE-Verified Leaderboard
1 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Google | — | 1.0M | $0.75 / $3.75 |
Notice missing or incorrect data?
What is HLE-Verified?
HLE-Verified evaluates multidisciplinary expert reasoning on a verified subset of Humanity's Last Exam.
HLE-Verified is a text benchmark evaluating models on knowledge and reasoning tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.5, with the leader at 0.5.
Compare leaders on the best AI for knowledge and best AI for reasoning leaderboards.
Current leaders
Gemini 3.7 Flash from Google currently leads the HLE-Verified leaderboard with a score of 0.536 across 1 evaluated AI models.
FAQ
Common questions about the HLE-Verified benchmark and leaderboard.