List your company

Plan Generation on Robo Challenge (Offline)

100Plan AccuracyCP-SAT Formalizer
9.41632.93356.4579.967May 31, 2026

Evaluation results

MethodLinks
CP-SAT FormalizerModel=Gemini-3-flash2026.05100
CP-SAT FormalizerModel=GPT-5-mini2026.0599.3
CP-SAT FormalizerModel=DeepSeek-V4-Flash2026.0597.9
CP-SAT FormalizerModel=Qwen3.6 35B A3B2026.0597.9
PDDL2.1 FormalizerModel=Qwen3.6 35B A3B2026.0567.9
PlannerModel=Qwen3.6 35B A3B2026.0559.3
PDDL2.1 FormalizerModel=GPT-5-mini2026.0555.7
PDDL2.1 FormalizerModel=Gemini-3-flash2026.0552.9
PlannerModel=GPT-5-mini2026.0546.4
PlannerModel=Gemini-3-flash2026.0540.7
PDDL2.1 FormalizerModel=DeepSeek-V4-Flash2026.0527.9
PlannerModel=DeepSeek-V4-Flash2026.0512.9