Constraint Satisfaction on Sudoku
57CSP Result Index 35DiffThinker
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DiffThinkerSetting=Flow Matching2025.12 | 57 | 95 | 98 | |
| DiffThinker++Setting=Flow Matching2025.12 | 55 | 94 | 97 | |
| Gemini-3-FlashSetting=N/A2025.12 | 3 | 29 | 69 | |
| Qwen3-VL-8BSetting=SFT2025.12 | 2 | 17 | 30 | |
| Qwen3-VL-32BSetting=SFT2025.12 | 2 | 22 | 32 | |
| GPT-5Setting=N/A2025.12 | 0 | 0 | 2 | |
| Qwen3-VL-8BSetting=N/A2025.12 | 0 | 0 | 0 | |
| Qwen3-VL-8BSetting=GRPO2025.12 | 0 | 0 | 0 | |
| Qwen3-VL-32BSetting=N/A2025.12 | 0 | 0 | 0 | |
| Qwen3-VL-32BSetting=GRPO2025.12 | 0 | 1 | 3 | |
| Qwen-Image-Edit-2509Setting=N/A2025.12 | 0 | 0 | 0 | |
| Qwen-Image-Edit-2511Setting=N/A2025.12 | 0 | 0 | 0 |