List your company

Mathematical Optimization Solving on ComplexLP

65.4AccuracyDCM-Agent
12.15225.97639.853.624Apr 22, 2026May 2, 2026May 13, 2026May 24, 2026Jun 3, 2026Jun 14, 2026Jun 25, 2026

Evaluation results

MethodLinks
DCM-AgentBackbone=GPT5.12026.0465.4
OptiTreeBackbone=GPT5.12026.0462.56
AF-MCTSBackbone=GPT5.12026.0460.66
OptiTreeModel=Gemini-3-Flash2026.0660.2
OptiMUSBackbone=GPT5.12026.0458.77
COOPAModel=GPT-5.22026.0655.9
Chain-of-ExpertsModel=GPT-5.22026.0655.5
Chain-of-ExpertsModel=o32026.0655.5
BaselineBackbone=GPT5.12026.0455.45
DCM-AgentBackbone=Qwen3-235B2026.0454.76
OptiTreeModel=GPT-5.22026.0653.6
COOPAModel=GPT-4.12026.0653.6
COOPAModel=o32026.0653.6
OptiTreeModel=Gemini-2.5-Flash2026.0653.6
DCM-AgentBackbone=Deepseek-V3.22026.0453.55
COOPAModel=GPT-52026.0653.1
OptiTreeModel=o4-mini2026.0652.6
OR-LLM-AgentModel=Gemini-3-Flash2026.0652.6
COOPAModel=Gemini-3-Flash2026.0652.6
OR-LLM-AgentModel=GPT-5.22026.0649.8
OptiTreeModel=GPT-4.12026.0649.3
Chain-of-ExpertsModel=Gemini-2.5-Flash2026.0649.3
OptiTreeBackbone=Qwen3-235B2026.0448.82
Chain-of-ExpertsModel=GPT-52026.0648.8
Chain-of-ExpertsModel=o4-mini2026.0648.3
OR-LLM-AgentModel=o32026.0647.9
COOPAModel=o4-mini2026.0647.9
OptiTreeBackbone=Deepseek-V3.22026.0447.87
OR-LLM-AgentModel=o4-mini2026.0647.4
Chain-of-ExpertsModel=Gemini-3-Flash2026.0647.4
COOPAModel=Gemini-2.5-Flash2026.0647.4
AF-MCTSBackbone=Qwen3-235B2026.0446.92
AF-MCTSBackbone=Deepseek-V3.22026.0446.92
OR-LLM-AgentModel=Gemini-2.5-Flash2026.0646.4
OptiTreeModel=Qwen3-30B†2026.0646.4
OR-LLM-AgentModel=GPT-4.12026.0645.5
OptiMUSBackbone=Qwen3-235B2026.0444.55
OptiMUSBackbone=Deepseek-V3.22026.0443.6
Chain-of-ExpertsModel=GPT-4.12026.0643.6
OptiTreeModel=GPT-52026.0643.1
OptiTreeModel=o32026.0643.1
Chain-of-ExpertsModel=Qwen3-30B†2026.0642.2
DCM-AgentBackbone=Qwen3-30B2026.0441.23
BaselineBackbone=Qwen3-235B2026.0440.76
OR-LLM-AgentModel=GPT-52026.0640.3
OptiMUSModel=GPT-4.12026.0639.3
OR-LLM-AgentModel=Qwen3-30B†2026.0638.9
OptiMUSModel=GPT-52026.0638.4
OptiMUSModel=Gemini-3-Flash2026.0638.4
BaselineBackbone=Deepseek-V3.22026.0438.39
OptiTreeBackbone=Qwen3-30B2026.0436.49
OptiMUSModel=o32026.0636
AF-MCTSBackbone=Qwen3-30B2026.0434.6
OptiMUSModel=o4-mini2026.0634.6
OptiMUSBackbone=Qwen3-30B2026.0433.64
DCM-AgentBackbone=Qwen3-8B2026.0432.23
COOPAModel=Qwen3-30B†2026.0632.2
BaselineBackbone=Qwen3-30B2026.0428.44
OptiMUSModel=Gemini-2.5-Flash2026.0627
OptiTreeBackbone=Qwen3-8B2026.0425.59
OptiMUSModel=Qwen3-30B†2026.0623.7
OptiMUSBackbone=Qwen3-8B2026.0423.22
AF-MCTSBackbone=Qwen3-8B2026.0419.43
BaselineBackbone=Qwen3-8B2026.0416.11
OptiMUSModel=GPT-5.22026.0614.2