Operations Research Problem Solving on MAMO ComplexLP
69.4Pass@1 AccuracyEvoOptiGraph
Evaluation Results
| Method | Links | |
|---|---|---|
| EvoOptiGraphParams=8B, Category=Fine-tuned LLMs2026.06 | 69.4 | |
| ORLMParams=8B, Category=Fine-tuned LLMs2026.06 | 59.5 | |
| DeepSeek-V3Params=671B, Category=Zero-shot LLMs2026.06 | 55 | |
| OptMATH (origin)Params=32B, Category=Fine-tuned LLMs2026.06 | 54.1 | |
| OptiMUS-v0.3Params=Closed, Category=Agentic Methods2026.06 | 52.1 | |
| CoEParams=Closed, Category=Agentic Methods2026.06 | 50.6 | |
| GPT-4oParams=Closed, Category=Zero-shot LLMs2026.06 | 46 | |
| LLMOPT (origin)Params=14B, Category=Fine-tuned LLMs2026.06 | 44.1 | |
| CoTParams=Closed, Category=Agentic Methods2026.06 | 42.3 | |
| Qwen2.5-72B-InstParams=72B, Category=Zero-shot LLMs2026.06 | 33.3 | |
| Qwen3-32BParams=32B, Category=Zero-shot LLMs2026.06 | 32.4 |