Mathematical Optimization Solving on ComplexLP
65.4AccuracyDCM-Agent
Evaluation Results
| Method | Links | |
|---|---|---|
| DCM-AgentBackbone=GPT5.12026.04 | 65.4 | |
| OptiTreeBackbone=GPT5.12026.04 | 62.56 | |
| AF-MCTSBackbone=GPT5.12026.04 | 60.66 | |
| OptiTreeModel=Gemini-3-Flash2026.06 | 60.2 | |
| OptiMUSBackbone=GPT5.12026.04 | 58.77 | |
| COOPAModel=GPT-5.22026.06 | 55.9 | |
| Chain-of-ExpertsModel=GPT-5.22026.06 | 55.5 | |
| Chain-of-ExpertsModel=o32026.06 | 55.5 | |
| BaselineBackbone=GPT5.12026.04 | 55.45 | |
| DCM-AgentBackbone=Qwen3-235B2026.04 | 54.76 | |
| OptiTreeModel=GPT-5.22026.06 | 53.6 | |
| COOPAModel=GPT-4.12026.06 | 53.6 | |
| COOPAModel=o32026.06 | 53.6 | |
| OptiTreeModel=Gemini-2.5-Flash2026.06 | 53.6 | |
| DCM-AgentBackbone=Deepseek-V3.22026.04 | 53.55 | |
| COOPAModel=GPT-52026.06 | 53.1 | |
| OptiTreeModel=o4-mini2026.06 | 52.6 | |
| OR-LLM-AgentModel=Gemini-3-Flash2026.06 | 52.6 | |
| COOPAModel=Gemini-3-Flash2026.06 | 52.6 | |
| OR-LLM-AgentModel=GPT-5.22026.06 | 49.8 | |
| OptiTreeModel=GPT-4.12026.06 | 49.3 | |
| Chain-of-ExpertsModel=Gemini-2.5-Flash2026.06 | 49.3 | |
| OptiTreeBackbone=Qwen3-235B2026.04 | 48.82 | |
| Chain-of-ExpertsModel=GPT-52026.06 | 48.8 | |
| Chain-of-ExpertsModel=o4-mini2026.06 | 48.3 | |
| OR-LLM-AgentModel=o32026.06 | 47.9 | |
| COOPAModel=o4-mini2026.06 | 47.9 | |
| OptiTreeBackbone=Deepseek-V3.22026.04 | 47.87 | |
| OR-LLM-AgentModel=o4-mini2026.06 | 47.4 | |
| Chain-of-ExpertsModel=Gemini-3-Flash2026.06 | 47.4 | |
| COOPAModel=Gemini-2.5-Flash2026.06 | 47.4 | |
| AF-MCTSBackbone=Qwen3-235B2026.04 | 46.92 | |
| AF-MCTSBackbone=Deepseek-V3.22026.04 | 46.92 | |
| OR-LLM-AgentModel=Gemini-2.5-Flash2026.06 | 46.4 | |
| OptiTreeModel=Qwen3-30B†2026.06 | 46.4 | |
| OR-LLM-AgentModel=GPT-4.12026.06 | 45.5 | |
| OptiMUSBackbone=Qwen3-235B2026.04 | 44.55 | |
| OptiMUSBackbone=Deepseek-V3.22026.04 | 43.6 | |
| Chain-of-ExpertsModel=GPT-4.12026.06 | 43.6 | |
| OptiTreeModel=GPT-52026.06 | 43.1 | |
| OptiTreeModel=o32026.06 | 43.1 | |
| Chain-of-ExpertsModel=Qwen3-30B†2026.06 | 42.2 | |
| DCM-AgentBackbone=Qwen3-30B2026.04 | 41.23 | |
| BaselineBackbone=Qwen3-235B2026.04 | 40.76 | |
| OR-LLM-AgentModel=GPT-52026.06 | 40.3 | |
| OptiMUSModel=GPT-4.12026.06 | 39.3 | |
| OR-LLM-AgentModel=Qwen3-30B†2026.06 | 38.9 | |
| OptiMUSModel=GPT-52026.06 | 38.4 | |
| OptiMUSModel=Gemini-3-Flash2026.06 | 38.4 | |
| BaselineBackbone=Deepseek-V3.22026.04 | 38.39 | |
| OptiTreeBackbone=Qwen3-30B2026.04 | 36.49 | |
| OptiMUSModel=o32026.06 | 36 | |
| AF-MCTSBackbone=Qwen3-30B2026.04 | 34.6 | |
| OptiMUSModel=o4-mini2026.06 | 34.6 | |
| OptiMUSBackbone=Qwen3-30B2026.04 | 33.64 | |
| DCM-AgentBackbone=Qwen3-8B2026.04 | 32.23 | |
| COOPAModel=Qwen3-30B†2026.06 | 32.2 | |
| BaselineBackbone=Qwen3-30B2026.04 | 28.44 | |
| OptiMUSModel=Gemini-2.5-Flash2026.06 | 27 | |
| OptiTreeBackbone=Qwen3-8B2026.04 | 25.59 | |
| OptiMUSModel=Qwen3-30B†2026.06 | 23.7 | |
| OptiMUSBackbone=Qwen3-8B2026.04 | 23.22 | |
| AF-MCTSBackbone=Qwen3-8B2026.04 | 19.43 | |
| BaselineBackbone=Qwen3-8B2026.04 | 16.11 | |
| OptiMUSModel=GPT-5.22026.06 | 14.2 |