Logical Reasoning on Sudoku (test)
99.9AccuracySePO-Generalist
Evaluation Results
| Method | Links | |
|---|---|---|
| SePO-GeneralistTask Agent=DeepSeek-V3.2, Prompt Agent=Gemini 3.1 Pro Preview2026.06 | 99.9 | |
| SePO-SpecialistTask Agent=DeepSeek-V3.2, Prompt Agent=Gemini 3.1 Pro Preview2026.06 | 99.8 | |
| Manual-CoTTask Agent=DeepSeek-V3.2, Prompt Agent=Gemini 3.1 Pro Preview2026.06 | 96.95 | |
| MetaSPOTask Agent=DeepSeek-V3.2, Prompt Agent=Gemini 3.1 Pro Preview2026.06 | 96.8 | |
| TextGradTask Agent=DeepSeek-V3.2, Prompt Agent=Gemini 3.1 Pro Preview2026.06 | 96.6 |