List your company

Plan Generation on Robo Challenge (Online)

85.7Plan AccuracyState-Aware CP-SAT Repair
-3.42819.71142.8565.989May 31, 2026

Evaluation results

MethodLinks
State-Aware CP-SAT RepairModel=Gemini-3-flash2026.0585.7
State-Aware CP-SAT RepairModel=Qwen3.6 35B A3B2026.0585
CP-SAT FormalizerModel=Gemini-3-flash2026.0583.6
State-Aware CP-SAT RepairModel=GPT-5-mini2026.0583.6
State-Aware CP-SAT RepairModel=DeepSeek-V4-Flash2026.0583.6
CP-SAT FormalizerModel=Qwen3.6 35B A3B2026.0572.1
PlannerModel=GPT-5-mini2026.0535
PlannerModel=Qwen3.6 35B A3B2026.0530.7
CP-SAT FormalizerModel=GPT-5-mini2026.0525
PlannerModel=Gemini-3-flash2026.0517.1
PlannerModel=DeepSeek-V4-Flash2026.0512.9
CP-SAT FormalizerModel=DeepSeek-V4-Flash2026.053.6
PDDL2.1 FormalizerModel=Gemini-3-flash2026.052.9
PDDL2.1 FormalizerModel=GPT-5-mini2026.050
PDDL2.1 FormalizerModel=DeepSeek-V4-Flash2026.050
PDDL2.1 FormalizerModel=Qwen3.6 35B A3B2026.050