NeSy-Route - Textual Constraint Understanding: leaderboard
Metric: Fully matching accuracy (%): share of queries whose traversability vector and preference ranking both match exactly, on NeSy-Route Task 1 (textual constraint understanding, 3,607 queries): from a natural-language route-planning query for a given agent and task, the model outputs which of 8 land-cover classes are traversable and their preference ranking, checked against knowledge-base ground truth; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.1 | 69.2 | #131 |
| 2 | Qwen 3.5 27B | 63.52 | #183 |
| 3 | Qwen 3 VL 235B A22B Instruct | 52.98 | #264 |
| 4 | Qwen 3 VL 30B A3B Instruct | 44.44 | #365 |
| 5 | Qwen 3 VL 32B Instruct | 31.69 | #276 |
| 6 | Qwen 3 VL 8B Instruct | 27.67 | #401 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=nesy-route-textual-constraint-understanding · How It Works · Data refreshed daily, snapshot 2026-10-11.