MulRobBench - Mean Dimension Score: leaderboard
Mean of the 12 MulRobBench scoring dimensions (2026), from operational context and evidence arbitration to degradation-aware reasoning and risk-aware action planning, under controlled semantic scoring. Percent, higher is better.
Metric: Semantic mean dimension score (%; mean over the 12 scoring dimensions; 3,024-sample strict evaluation set of real UAV observations with protocol constraints, degradations and operator language; controlled semantic scores in [0, 1] x100). Source: arxiv.org. Saturation forecast: Around 2029. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 9B | 48.15 | #803 |
| 2 | Qwen 3.5 4B | 42.93 | #1175 |
| 3 | Qwen 3.5 2B | 40.8 | #4810 |
| 4 | Gemma 4 E2B | 38.21 | #3892 |
| 5 | Qwen 2.5 VL 7B | 37.98 | #1787 |
| 6 | Gemma 4 E4B | 36.3 | #2214 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=mulrobbench-mean-dimension-score · How It Works · Data refreshed daily, snapshot 2026-11-13.