Artificial Analysis Says GPT-6 Astra Leads Robot Arm Test at 69
Summary
Artificial Analysis releases AA-Robotics v0.1, a research preview testing frontier language models on controlling a 6-axis robot arm across eight tabletop tasks. GPT-6 Astra leads with a score of 69, averaging 30 minutes and $16.36 per task. The firm says models run about 100 times slower than humans.
Key Points
- Artificial Analysis reports GPT-6.1 Sol is the cheapest model, at $1.93 per task on average.
- The human baseline averages 20 seconds per task, priced at $37.81 per hour per US Bureau of Labor Statistics data.
- Gemini 4 Argon is the slowest model, averaging 52.4 minutes per task, Artificial Analysis says.