跳到正文
实时
Artificial Analysis Articles·· 2026-10-14

AA-Robotics v0.1 发布

Welcome to the era of embodied AI: Introducing AA-Robotics v0.1

要点速览

AA-Robotics v0.1 在 8 项任务中取得平均 69.4 分,优于 GPT-6(64.6 分)、GPT-6.1(55.3 分)、Gemini 4 Argon(48.8 分)、Claude Opus 5.5(46.3 分),在 7 项任务中得分满分。各模型在 Codex、Claude Code 或 Antigravity 中以高努力度运行。

正文

Introducing AA-Robotics v0.1

The eight tasks

Results

Results per Task

  • Full score (100)
  • Partial (1 to 99)
  • Zero (0)
Task

GPT-6 Astra

GPT-6.1 Sol

Gemini 4 Argon

Claude Opus 5.5

Claude Fable 5.1

Press the red button

Full score, 100 of 100

Full score, 100 of 100

Full score, 100 of 100

Full score, 100 of 100

Full score, 100 of 100

Place the crocodile toy in the rectangle

Full score, 100 of 100

Full score, 100 of 100

Full score, 100 of 100

Full score, 100 of 100

Full score, 100 of 100

Pour the drink into the cup

Full score, 100 of 100

Zero, 0 of 100

Full score, 100 of 100

Partial, 25 of 100

Partial, 30 of 100

Tidy the blocks into the box

Partial, 40 of 100

Full score, 100 of 100

Partial, 40 of 100

Partial, 40 of 100

Partial, 40 of 100

Complete the shape matching challenge

Partial, 44 of 100

Full score, 100 of 100

Zero, 0 of 100

Partial, 38 of 100

Full score, 100 of 100

Write hello world

Full score, 100 of 100

Full score, 100 of 100

Partial, 45 of 100

Partial, 45 of 100

Zero, 0 of 100

Build the tallest tower

Partial, 71 of 100

Zero, 0 of 100

Partial, 57 of 100

Partial, 25 of 100

Zero, 0 of 100

Measure the box

Zero, 0 of 100

Partial, 17 of 100

Zero, 0 of 100

Partial, 17 of 100

Zero, 0 of 100

AA-Robotics Score69.464.655.348.846.3

Each attempt is scored out of 100: completing the task scores 100, and a partial result earns points for the progress made.

GPT models run in Codex, Claude models in Claude Code, and Gemini 4 Argon in Antigravity, all at the high effort setting.

How AA-Robotics works

Time & cost

How each model spent its time

Physical accuracy

Mistake wall

来源: Artificial Analysis Articles · artificialanalysis.ai