VLAN - Real World 30 Trajectories - 𝐒𝐑lan𝐚𝐯𝐠 ↑: 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: Around 2028. 7 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1Qwen 2.5 VL 3B Instruct0.233#2648
2Qwen 3 VL 8B Instruct0.2#1025
3InternVL3.5-8B0.2#1588
4Qwen 2.5 VL 7B Instruct0.189#1893
5Llama 3.2 11B Instruct0.133#5226
6Molmo2-8B0.133#1629
7Idefics3-8B-Llama30.111#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-real-world-30-trajectories-lan Β· How It Works Β· Data refreshed daily, snapshot 2026-11-17.