Agents' Last Exam Overall Score
Agents · 2026-06-03
Average partial-credit rubric score across the full 152-task Agents' Last Exam set, reported separately from the stricter perfect-score pass rate.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 53.6 |
| Kimi K3 | 51.6 |
| GPT-5.6 Terra | 50.5 |
| GPT-5.6 Luna | 50.3 |
| Claude Fable 5 | 48.7 |
| GPT-5.5 | 47.9 |
| Opus 4.8 | 45.2 |
| Opus 4.7 | 41.8 |
| Doubao Seed 2.1 Pro | 41.4 |
| GLM-5.2 | 40.6 |
| Composer 2.5 | 38.5 |
| GPT-5.4 | 37.3 |
| Gemini 3.1 Pro Preview | 32.1 |
| Qwen3.7-Max | 31.1 |
| GLM-5.1 | 28.1 |
| DeepSeek-V4-Pro | 27.6 |
| Qwen3.6 Plus (2026-04-02) | 24.3 |
| MiMo-V2.5 | 23.6 |
| Kimi K2.6 | 21.7 |
| Grok 4.3 | 20.1 |
| MiniMax M2.7 | 14.2 |