VLAN - Quadruped Full Split - Collision Free: 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: Estimated already saturated. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Qwen 2.5 VL 3B Instruct0.983#2648
2Llama 3.2 11B Instruct0.893#5226
3Molmo2-8B0.83#1629
4InternVL3.5-8B0.808#1588
5Qwen 3 VL 8B Instruct0.77#1025
6Qwen 2.5 VL 7B Instruct0.741#1893
7Idefics3-8B-Llama30.65#5775

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-collision-free · How It Works · Data refreshed daily, snapshot 2026-11-17.