Reasoning on HMMT Feb26 (Avg@64)
95.64Avg@64OpenAI GPT-5.4
Evaluation Results
| Method | Links | |
|---|---|---|
| OpenAI GPT-5.42026.06 | 95.64 | |
| DS-V4-Pro2026.06 | 95.2 | |
| Claude Opus-4.72026.06 | 94.08 | |
| Ring-2.6-1Tvariant=xhigh2026.06 | 93.47 | |
| Kimi-K2.62026.06 | 92.7 | |
| Claude Opus-4.62026.06 | 83.38 | |
| Ring-2.6-1Tvariant=high2026.06 | 67.8 |