VLAN - Quadruped Full Split - Success: leaderboard
Full1931trajectorysplit, quadrupedactionprediction; jointgoal+clearancesuccess. EntirequadrupedpopulationpassesSR<=GR, SPL<=SR. Dronefamilyhasseparateunresolvedsourcecontradictionandisnotincluded. Metric: Native rate (0–1). Source: https://arxiv.org/html/2611.18346v1
Metric: Native rate (0–1). Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 17 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 0.474 | #1025 |
| 2 | InternVL3.5-8B | 0.393 | #1588 |
| 3 | Qwen 2.5 VL 7B Instruct | 0.384 | #1893 |
| 4 | Idefics3-8B-Llama3 | 0.308 | #5775 |
| 5 | Molmo2-8B | 0.147 | #1629 |
| 6 | Qwen 2.5 VL 3B Instruct | 0.053 | #2648 |
| 7 | Llama 3.2 11B Instruct | 0.048 | #5226 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=vlan-quadruped-full-split-success · How It Works · Data refreshed daily, snapshot 2026-11-17.