Makespan Accuracy on Robotouille
20Makespan AccuracyGemini-3-flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-flashApproach=PDDL2.1 Formalizer2026.05 | 20 | |
| GPT-5-miniApproach=PDDL2.1 Formalizer2026.05 | 20 | |
| DeepSeek-V4-FlashApproach=PDDL2.1 Formalizer2026.05 | 20 | |
| Qwen3.6 35B A3BApproach=PDDL2.1 Formalizer2026.05 | 10 | |
| Gemini-3-flashApproach=Planner2026.05 | 0 | |
| Gemini-3-flashApproach=CP-SAT Formalizer2026.05 | 0 | |
| GPT-5-miniApproach=Planner2026.05 | 0 | |
| GPT-5-miniApproach=CP-SAT Formalizer2026.05 | 0 | |
| DeepSeek-V4-FlashApproach=Planner2026.05 | 0 | |
| DeepSeek-V4-FlashApproach=CP-SAT Formalizer2026.05 | 0 | |
| Qwen3.6 35B A3BApproach=Planner2026.05 | 0 | |
| Qwen3.6 35B A3BApproach=CP-SAT Formalizer2026.05 | 0 |