RobotWorld - Aerial: leaderboard
RobotWorld:84tasks from20projects,one episode/model/task Sept30–Oct6,2026;fixed domain partition38/20/11/11/4. Direct robot tools,environment-side code control disabled,up to4earlier observations every2rounds. Success at applicable control/non-action budget boundary,retrospective adjudication preserved. Not interchangeable with RoboUse live aggregate or VLA LIBERO cohort. Tasks solved (/4).
Metric: Tasks solved (/4). Source: arxiv.org. Saturation forecast: Around March 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 | 3 | #4 |
| 2 | GPT-6 Astra | 1 | #6 |
| 3 | DeepSeek V4.1 Flash | 1 | #34 |
| 4 | Kimi K3 | 0 | #32 |
| 5 | Gemini 3.8 Flash | 0 | #24 |
No result here: #7 GPT-6.1 Sol, #8 Gemini 4 Argon, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=robotworld-aerial · How It Works · Data refreshed daily, snapshot 2026-10-24.