Strategic Reasoning on SepaRank Arm PC ten games (program / committed)
12.9Total Score (G)gpt-5.5
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| gpt-5.5Arm=PC (program / committed)2026.07 | 12.9 | 0.384 | 0.054 | 0.416 | 59 | |
| gpt-5.4Arm=PC (program / committed)2026.07 | 9.7 | 0.367 | 0.082 | 0.24 | 79.5 | |
| gpt-4o-miniArm=PC (program / committed)2026.07 | 6.9 | 0.068 | 0.254 | 0.019 | 89.5 | |
| deepseek-v4-proArm=PC (program / committed)2026.07 | 5.2 | 0.076 | 0.213 | 0.026 | 77.1 | |
| kimi-k2.7Arm=PC (program / committed)2026.07 | 4.7 | 0.143 | 0.21 | 0.022 | 82.2 | |
| gpt-5.4-nanoArm=PC (program / committed)2026.07 | 4.6 | 0.122 | 0.178 | 0.024 | 94.5 | |
| haiku-4.5Arm=PC (program / committed)2026.07 | 4.3 | 0.078 | 0.169 | 0.024 | 90.1 | |
| qwen3.7-maxArm=PC (program / committed)2026.07 | 3.3 | 0.194 | 0.107 | 0.09 | 99 | |
| gpt-5.4-miniArm=PC (program / committed)2026.07 | 1.3 | 0.187 | 0.126 | 0.055 | 94.5 | |
| sonnet-4.6Arm=PC (program / committed)2026.07 | 1 | 0.093 | 0.122 | 0.041 | 94.4 | |
| opus-4.8Arm=PC (program / committed)2026.07 | 0.4 | 0.086 | 0.095 | 0.043 | 97.5 |