RoboProcessBench - Bimanual Coordination: leaderboard

Metric: Accuracy (%) on 533 questions asking how the two arms are currently coordinating, from a short ordered clip (4 options, chance 25.0); zero-shot multiple-choice VQA on held-out robot manipulation recordings from GM-100, RH20T, REASSEMBLE and AIST-Bimanual (ProcessData-Eval), temperature 0.01; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 14 models tracked.

Top models

#ModelScore
1Qwen 3 VL 32B41.9
2GPT-4o40
3Claude Haiku 4.539.5
4GPT-5.4 Mini38.1
5Qwen 2.5 VL 7B Instruct36.4
6Claude Sonnet 4.636.3
7InternVL3.5-8B26.5
8GLM-4.6V26
9InternVL3-38B25.1
10InternVL3-8B22.9

Interactive version: theaggregate.ai/benchmark?slug=roboprocessbench-bimanual-coordination · How It Works · Data refreshed daily, snapshot 2026-09-29.