NeSy-Route - Route Planning Adherence: leaderboard
Metric: Adherence rate (%): share of samples whose predicted waypoints all lie in traversable regions, on NeSy-Route Task 3 (constrained route planning, 10,821 samples in Easy, Medium and Hard tiers): the model outputs sparse waypoints from start to end on a remote-sensing image under the query's traversability and cost constraints; mean of the three tier scores; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 32B Instruct | 32.7 | #276 |
| 2 | Qwen 3 VL 235B A22B Instruct | 27.8 | #264 |
| 3 | Qwen 3 VL 8B Instruct | 27.63 | #401 |
| 4 | Qwen 3 VL 30B A3B Instruct | 24.97 | #365 |
| 5 | Qwen 3.5 27B | 20.1 | #183 |
| 6 | Gemini 3 Pro | 18.7 | #77 |
| 7 | GPT-5.1 | 17.63 | #131 |
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-route-planning-adherence · How It Works · Data refreshed daily, snapshot 2026-10-11.