AA-Robotics v0.1 leaderboard
Artificial Analysis research preview in which frontier language models, run as coding agents (Codex, Claude Code, Antigravity), drive a real arm through an HTTP API and four cameras. Only general LLMs are evaluated, not VLAs; a human grader scores each attempt against the task’s pass criteria.
Real robot · Hiwonder NexArm (6-axis)Report an error
79Best · GPT-6.2 Astra
9Models ranked
OpenSaturation
Nov 18, 2026Numbers checked
| # | Model | Type | Score | Date | Source |
|---|---|---|---|---|---|
| 1 | LLM controller | 79 | Nov 17, 2026 | ||
| 2 | LLM controller | 78 | Nov 17, 2026 | ||
| 3 | LLM controller | 75 | Nov 17, 2026 | ||
| 4 | LLM controller | 69.4 | Oct 14, 2026 | ||
| 5 | LLM controller | 64.6 | Oct 14, 2026 | ||
| 6 | LLM controller | 58, self-reported by the authors, not a leaderboard entry | Nov 17, 2026 | ||
| 7 | LLM controller | 55.3 | Oct 14, 2026 | ||
| 8 | LLM controller | 48.8 | Oct 14, 2026 | ||
| 9 | LLM controller | 46.3 | Oct 14, 2026 |
Metric: Mean human-graded score (0–100, partial credit) over 8 zero-shot tabletop tasks, one attempt each. One result per model: RoboFYI re-run, then official leaderboard, then paper, then third party. Runs that deviate from the official protocol are listed on the model page but not ranked.
Wrong or missing number? Report an error