Text2Opt-Bench - Multi-Objective Transportation: leaderboard
Bi-objective transportation MILPs trading cost against emissions, with fixed charges, minimum order quantities and supplier limits, from Text2Opt-Bench (Gao, Ge, Berenbeim, Bastian and Sala, 2026): the model reads the problem and its instance data in natural language and writes Gurobi code, and an answer counts when the solved objective matches the verified optimum. Pass@1 accuracy in percent on 50 problems; higher is better.
Metric: Pass@1 accuracy (%; bi-objective cost and emissions transportation MILP with fixed charges, 50 instances; solver-verified optimal objective). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 98 | #158 |
| 2 | Claude Opus 4.6 | 88 | #100 |
| 3 | DeepSeek V3.2 | 86 | #403 |
| 4 | DeepSeek R1 | 76 | #467 |
| 5 | GPT-5 | 70 | #163 |
| 6 | O4 Mini | 68 | #354 |
| 7 | GPT-5 Nano | 60 | #888 |
| 8 | Llama 3.3 70B Instruct | 42 | #1353 |
| 9 | Qwen 2.5 7B Instruct | 4 | #2583 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=text2opt-bench-multi-objective-transportation · How It Works · Data refreshed daily, snapshot 2026-11-12.