| Rank | Model | Score |
|---|---|---|
| 1 | gemini-4-argon | 77.9 |
| 2 | deepseek-v4-1-flash-1017 | 77 |
| 3 | kimi-k3-1-pro | 75.5 |
| 4 | deepseek-v4-1-flash | 74.2 |
| 5 | deepseek-v4-1-flash | 74.2 |
| 6 | gpt-6-astra | 74.1 |
| 7 | minimax-m3-1-flash | 73.7 |
| 8 | mimo-v2-6-pro-rl | 71.9 |
| 9 | grok-4-7 | 71 |
| 10 | gpt-6-sol | 68.8 |
| 11 | mimo-v2-6-flash-rl | 67.9 |
| 12 | kimi-k3 | 67.5 |
| 13 | glm-5-3 | 66.9 |
| 14 | gpt-6-luna | 66.6 |
| 15 | grok-4-6 | 65.9 |
| 16 | nex-n2-5-max | 65.6 |
| 17 | nanbeige4-3-33b | 65.5 |
| 18 | hy4-preview | 64.3 |
| 19 | glm-5-3-flash | 63.4 |
| 20 | deepseek-v4-pro | 62.7 |
| 21 | muse-spark-open-816b-a42b | 60 |
| 22 | ling-3-1-flash-1019 | 59.7 |
| 23 | ling-3-1-flash-1019 | 59.7 |
| 24 | muse-spark-1-2 | 59.3 |
| 25 | deepseek-v4-flash-vision-exp | 59.3 |
1 phaseActive