Text2Opt-Bench - Resource Allocation: leaderboard
Metric: Pass@1 accuracy (%; direct-translation LP/MILP resource allocation, 248 evaluation instances with 2-20 variables; solver-verified optimal objective). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 89.9 |
| 2 | GPT-5 | 87.9 |
| 3 | Claude Sonnet 4.6 | 84.7 |
| 4 | DeepSeek R1 | 80.6 |
| 5 | O4 Mini | 80.2 |
| 6 | DeepSeek V3.2 | 79 |
| 7 | Llama 3.3 70B Instruct | 49.6 |
| 8 | GPT-5 Nano | 49.2 |
| 9 | Qwen 2.5 7B Instruct | 13.3 |
Interactive version: theaggregate.ai/benchmark?slug=text2opt-bench-resource-allocation · How It Works · Data refreshed daily, snapshot 2026-09-26.