Native Robot Reasoning - RoboLab-120 - Progress Score: leaderboard
120 tasks (64 simple, 39 moderate, 17 complex), 10episodes/task. Author-run Qwen3.8-27B baseline; other robot-policy values are cited existing leaderboard results; Ours is a distinct trained model, not the base model. Metric: Progress score (%). Source: https://arxiv.org/html/2611.18562v1
Metric: Progress score (%). Source: arxiv.org. 1 model tracked. Updated 17 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen3.8-27B | xHigh | 12.1 |
Interactive version: theaggregate.ai/benchmark?slug=native-robot-reasoning-robolab-120-progress-score · How It Works · Data refreshed daily, snapshot 2026-11-17.