List your company

Operations Research Modeling and Solving on NEXTOR

76.31Accuracy (pass@1)NEDTree
-0.317219.576439.4759.3636Apr 2, 2026

Evaluation results

MethodLinks
NEDTreeType=Context-based2026.0476.31
GPT-o4-miniType=Reasoning2026.0452.63
ORllmAgentType=Prompt-based2026.0452.63
Chain-of-ExpertsType=Prompt-based2026.0451.32
Deepseek-R1Type=Reasoning2026.0440.79
Deepseek-V3Type=Non-reasoning2026.0426.31
GPT-4oType=Non-reasoning2026.0418.42
OptimusType=Prompt-based2026.0418.42
ORLM(best)Type=Fine-tuning2026.0411.84
LLMOPTType=Fine-tuning2026.042.63