GPT-6 Astra appears to show a "step change" in spatial reasoning based on early benchmarks
Early StationeryBench robotics results show OpenAI's GPT-6 Astra far ahead of Ai2's MolmoAct2 at dual-arm manipulation, completing 7 of 100 tasks versus zero.
A new robotics benchmark called StationeryBench tested OpenAI's GPT-6 Astra against Ai2's MolmoAct2 on five desk-object tasks using identical dual-arm YAM robots over 200 trials. Astra fully completed 7 of 100 tasks with a median progress score of 46 out of 100, while MolmoAct2 completed zero with a median score of 12. Cornell and Google DeepMind researcher Yoav Artzi called the result a 'step change in spatial reasoning' and noted Astra approaches human-level accuracy on the unpublished REMAP benchmark. He speculated OpenAI trained the model on large amounts of 3D data such as Blender scenes, and OpenAI reportedly plans consumer robots.
- Astra completed 7 of 100 StationeryBench tasks with dual-arm YAM robots; MolmoAct2 completed zero
- Median progress scores: Astra 46/100 vs MolmoAct2 12/100 across 200 trials
- Yoav Artzi calls Astra a 'step change in spatial reasoning'; REMAP accuracy nears human level
- Artzi suspects training on large 3D datasets such as Blender scenes; OpenAI weighs consumer robots
- Organizations
- OpenAIAi2CornellGoogle DeepMind
- AI models
- GPT-6 AstraMolmoAct2
From the original article
1 min read at the-decoder.com
In a new robotics benchmark, GPT-6 Astra shows major gains in spatial understanding. On StationeryBench, the model completed 7 out of 100 tasks with dual-arm robots, while competitor MolmoAct2 couldn't finish a single one. A researcher calls it a "step change in spatial reasoning."
By Matthias Bastian · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.