Knowledge
Humanity's Last Exam Leaderboard
Humanity's Last Exam (HLE) is a set of extremely difficult, expert-written questions across many fields, designed so that even frontier models score low. It is built to stay hard as models improve, measuring the true knowledge frontier.
Source: epoch4 open models ranked+47 proprietaryData through Oct 2026
Open models ranked on Humanity's Last Exam
# shows rank among open models / rank overall (including proprietary).
| # | Model | Score | VRAM @ Q4 |
|---|---|---|---|
| 1 / 18 | Kimi K2.5 · 1026.9B | 24.4% | ~620 GB |
| 2 / 35 | GLM 4.5 · 358.3B | 8.3% | ~216 GB |
| 3 / 36 | GLM 4.5 Air · 110.5B | 8.1% | ~67 GB |
| 4 / 43 | Llama 4 Maverick 17B 128E Instruct · 401.6B | 5.7% | ~265 GB |
Humanity's Last Exam: frequently asked questions
- What is the best open LLM on Humanity's Last Exam?
- Kimi K2.5 is the top open model on Humanity's Last Exam, scoring 24.4%. Among all models tested — including proprietary ones — it ranks #18. The top model overall is GPT 6 Astra (unspecified) (OpenAI) at 54.8%.
- Can open models match proprietary models on Humanity's Last Exam?
- Not quite on Humanity's Last Exam: the strongest proprietary model (GPT 6 Astra (unspecified)) scores 54.8%, ahead of the best open model (Kimi K2.5) at 24.4% — but you can run the open one yourself.
Scores aggregated from epoch. llmrun does not run this benchmark — see the source for methodology, or the about benchmarks for what it measures.