Robotics
Task 41 / 47
UAVInspectionCoverageWithWind
UAV inspection coverage planning under wind disturbance: optimize paths or controls to maximize inspected area or revisit metrics while managing energy and safety margins. Wind fields couple geometric coverage with uncertainty, scored by coverage fraction and mission success in simulation.
Model leaderboard
Updated v1 results · 2026-09-15 · raw score, higher is better.
| # | Participant | Raw score | Medal |
|---|---|---|---|
| 1 | Grok 4.20 | 55.9109 | Gold |
| 2 | DeepSeek V3.2 | 38.8024 | Silver |
| 3 | GLM-5 | 35.1121 | Bronze |
| 4 | Qwen3 Coder Next | 32.8468 | — |
| 5 | Seed 2.0 Pro | 32.1552 | — |
| 6 | GPT-5.4 | 30.121715 | — |
| 7 | Claude Opus 4.6 | 28.8519 | — |
| 7 | Gemini 3.1 Pro Preview | 28.8519 | — |
Framework results · original paper
Historical results from the original evaluators · normalized score (0–100).
| # | Participant | Score |
|---|---|---|
| 1 | GPT-OSS + OpenEvolve | 100.0 |
| 2 | Claude Opus 4.6 + ShinkaiEvolve | 31.7 |
| 3 | Claude Opus 4.6 + ABMCTS | 20.3 |
| 4 | GPT-OSS + ShinkaiEvolve | 7.3 |
| 5 | Claude Opus 4.6 + OpenEvolve | 0.0 |
| 6 | GPT-OSS + ABMCTS | 0.0 |
Model results use the updated scores and medal thresholds. No valid score earns zero medal credit. Historical framework scores use the original evaluators and have not been updated alongside the model results.