Agents' Last Exam Benchmark Scores
Full / Overall pass rates from Agents' Last Exam. Color = provider.
Agents' Last Exam Benchmark Scores
Full / Overall pass rates from Agents' Last Exam. Color = provider.
How To Read This Chart
This benchmark chart uses source-backed benchmark rows mapped to public AI IQ model profiles.
Top Models
| Rank | Model | Provider | Score |
|---|---|---|---|
| 1 | gpt-5.5 | OpenAI | 24 |
| 2 | gpt-5.4 | OpenAI | 20.5 |
| 3 | opus-4.7 | Anthropic | 18.4 |
| 4 | gemini-3.1-pro | 15.8 | |
| 5 | opus-4.8 | Anthropic | 15.8 |
| 6 | opus-4.6 | Anthropic | 14.1 |
| 7 | deepseek-v4-pro | DeepSeek | 12.4 |
| 8 | qwen3.7-max | Alibaba | 11.8 |
| 9 | glm-5.1 | Z.ai | 11.5 |
| 10 | kimi-k2.6 | Kimi | 9.2 |
| 11 | mimo-v2.5 | Xiaomi | 8.6 |
| 12 | qwen3.6-plus | Alibaba | 8.6 |