Mathematical Optimization Solving on IndOR
53AccuracyDCM-Agent
Evaluation Results
| Method | Links | |
|---|---|---|
| DCM-AgentBackbone=GPT5.12026.04 | 53 | |
| AF-MCTSBackbone=GPT5.12026.04 | 51 | |
| OptiTreeBackbone=GPT5.12026.04 | 49 | |
| OptiMUSBackbone=GPT5.12026.04 | 46 | |
| BaselineBackbone=GPT5.12026.04 | 44 | |
| DCM-AgentBackbone=Deepseek-V3.22026.04 | 41 | |
| DCM-AgentBackbone=Qwen3-235B2026.04 | 40 | |
| AF-MCTSBackbone=Deepseek-V3.22026.04 | 39 | |
| OptiTreeBackbone=Deepseek-V3.22026.04 | 38 | |
| AF-MCTSBackbone=Qwen3-235B2026.04 | 37 | |
| OptiTreeBackbone=Qwen3-235B2026.04 | 36 | |
| OptiMUSBackbone=Deepseek-V3.22026.04 | 36 | |
| DCM-AgentBackbone=Qwen3-30B2026.04 | 34 | |
| OptiMUSBackbone=Qwen3-235B2026.04 | 34 | |
| BaselineBackbone=Deepseek-V3.22026.04 | 34 | |
| BaselineBackbone=Qwen3-235B2026.04 | 32 | |
| AF-MCTSBackbone=Qwen3-30B2026.04 | 31 | |
| DCM-AgentBackbone=Qwen3-8B2026.04 | 30 | |
| OptiTreeBackbone=Qwen3-30B2026.04 | 30 | |
| OptiMUSBackbone=Qwen3-30B2026.04 | 29 | |
| OptiTreeBackbone=Qwen3-8B2026.04 | 25 | |
| BaselineBackbone=Qwen3-30B2026.04 | 25 | |
| OptiMUSBackbone=Qwen3-8B2026.04 | 23 | |
| AF-MCTSBackbone=Qwen3-8B2026.04 | 21 | |
| BaselineBackbone=Qwen3-8B2026.04 | 19 |