Optimization Modeling on IndustryOR (SA)
84.34SA ScoreOptiAgent
Evaluation Results
| Method | Links | |
|---|---|---|
| OptiAgentBackbone=GPT 5.42026.07 | 84.34 | |
| GPT 5.2System Prompt=with2026.07 | 72.297 | |
| OptiAgentBackbone=Sonnet 4.52026.07 | 71.08 | |
| Sonnet 4.5System Prompt=with2026.07 | 67.47 | |
| GPT 5.4System Prompt=without2026.07 | 67.07 | |
| GPT 5.2System Prompt=without2026.07 | 66.27 | |
| GPT 5.4System Prompt=with2026.07 | 65.85 | |
| SonnetSystem Prompt=without2026.07 | 63.86 | |
| NEMO2026.07 | 63 | |
| ORThought2026.07 | 57.83 | |
| DeepSeek-R1System Prompt=with2026.07 | 51.81 | |
| DeepSeekSystem Prompt=without2026.07 | 46.99 | |
| LLMOPT2026.07 | 46 | |
| CoE2026.07 | 40.96 | |
| ORLM2026.07 | 32.13 |