StrongREJECT — Results
| Rank | Model | Score |
|---|---|---|
| 1 | kimi-k2-6 | 99.8 |
| 2 | kimi-k2-5 | 99.5 |
| 3 | claude-fable-5 | 98.7 |
| 4 | nemotron-3-ultra-550b-a55b | 98.7 |
| 5 | deepseek-v4-pro | 98.6 |
| 6 | inkling | 98.6 |
| 7 | glm-5-2 | 98.5 |
| 8 | gpt-5-6-sol | 98.5 |
| 9 | gemini-3-1-pro | 98 |
StrongREJECT — Evaluations
1 phaseActive
No evaluations yet for this benchmark.