VLAN - Matched 200 Trajectories - Humanoid: leaderboard

Independent evaluation cohort. S4T7=30real-worldtrajectories; language/actionfamilymeans andharmonicAccSR. A4T14=fixed200testtrajectories, 2/scene, seed42, nineVLMs, identicalbudget; notinterchangeablewith1931fullsplit. FullsplitDroneSRact/GRinconsistency held separately. Metric: Native success score (0–1). Source: https://arxiv.org/html/2611.18346v1

Metric: Native success score (0–1). Source: arxiv.org. Saturation forecast: Not forecast. 8 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Llama 3.2 11B Instruct0.565#5226
2Molmo2-8B0.535#1629
3Qwen 2.5 VL 3B Instruct0.525#2648
4GPT-4o0.465#754
5Idefics3-8B-Llama30.445#5775
6Qwen 3 VL 8B Instruct0.41#1025
7InternVL3.5-8B0.39#1588
8Qwen 2.5 VL 7B Instruct0.27#1893

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=vlan-matched-200-trajectories-humanoid · How It Works · Data refreshed daily, snapshot 2026-11-17.