List your company

Constraint Satisfaction on SudokuBench

74.7AccuracyGemini 2.5 Pro+ASP
-1.94817.95137.8557.749Apr 30, 2026

Evaluation results

MethodLinks
Gemini 2.5 Pro+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0474.7
DS-R1-0528+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0470
o4-mini+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0467
Gemini 2.5 Flash+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0465.7
DS-V3+ASPInference Pipeline=LLM+ASP, Prompt Reference Type=Compact Reference2026.0421.7
o4-miniInference Pipeline=Baseline2026.0415
Gemini 2.5 ProInference Pipeline=Baseline2026.0410.3
DS-R1-0528Inference Pipeline=Baseline2026.048.3
Gemini 2.5 FlashInference Pipeline=Baseline2026.047.3
DS-V3Inference Pipeline=Baseline2026.041