Constraint Satisfaction on SudokuBench
74.7AccuracyGemini 2.5 Pro+ASP
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 2.5 Pro+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.04 | 74.7 | |
| DS-R1-0528+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.04 | 70 | |
| o4-mini+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.04 | 67 | |
| Gemini 2.5 Flash+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.04 | 65.7 | |
| DS-V3+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.04 | 21.7 | |
| o4-miniInference Pipeline=Baseline2026.04 | 15 | |
| Gemini 2.5 ProInference Pipeline=Baseline2026.04 | 10.3 | |
| DS-R1-0528Inference Pipeline=Baseline2026.04 | 8.3 | |
| Gemini 2.5 FlashInference Pipeline=Baseline2026.04 | 7.3 | |
| DS-V3Inference Pipeline=Baseline2026.04 | 1 |