Text2Opt-Bench - Stochastic Transportation: leaderboard
Metric: Pass@1 accuracy (%; two-stage stochastic MILP with sample-average approximation and chance constraints, 50 instances; solver-verified optimal objective). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 70 |
| 2 | O4 Mini | 66 |
| 3 | Claude Sonnet 4.6 | 62 |
| 4 | Claude Opus 4.6 | 62 |
| 5 | DeepSeek R1 | 60 |
| 6 | GPT-5 Nano | 32 |
| 7 | DeepSeek V3.2 | 18 |
| 8 | Llama 3.3 70B Instruct | 6 |
| 9 | Qwen 2.5 7B Instruct | 0 |
Interactive version: theaggregate.ai/benchmark?slug=text2opt-bench-stochastic-transportation · How It Works · Data refreshed daily, snapshot 2026-09-26.