General QA on GPQA Diamond
69.19Exact MatchDeepSeek-R1
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSeek-R12025.12 | 69.19 | |
| CompassMax-V3-Thinking2025.12 | 68.69 | |
| CompassMax-V32025.12 | 44.44 |
| Method | Links | |
|---|---|---|
| DeepSeek-R12025.12 | 69.19 | |
| CompassMax-V3-Thinking2025.12 | 68.69 | |
| CompassMax-V32025.12 | 44.44 |