Text2Opt-Bench - Vehicle Routing with Time Windows: leaderboard
Metric: Pass@1 accuracy (%; vehicle routing MILP with time windows, capacity and subtour elimination, 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 | Claude Sonnet 4.6 | 50 |
| 3 | Claude Opus 4.6 | 38 |
| 4 | DeepSeek R1 | 34 |
| 5 | O4 Mini | 34 |
| 6 | DeepSeek V3.2 | 22 |
| 7 | GPT-5 Nano | 2 |
| 8 | Llama 3.3 70B Instruct | 0 |
| 9 | Qwen 2.5 7B Instruct | 0 |
Interactive version: theaggregate.ai/benchmark?slug=text2opt-bench-vehicle-routing-with-time-windows · How It Works · Data refreshed daily, snapshot 2026-09-26.