GPT-6.2 Astra tops RoboColosseum's SO-ARM101 robot leaderboard
OpenAI's GPT-6.2 Astra ranks first on the SO-ARM101 open track leaderboard run by RoboColosseum. The leaderboard rates robot policies from blind comparisons in scenes they have never seen, judged by people, with a separate leaderboard for each robot.
The entry gpt-6-2-astra-so101 has a rating of 1,984 (±96) from 122 comparisons. It sits 181 points ahead of Anthropic's claude-fable-5-2-so101 at 1,803 (±91), and the leaderboard says that lead is inside the error bars. Anthropic's Claude Opus 5.5 entry ranks third at 1,666 and Physical Intelligence's pi05 fourth at 1,525. OpenAI's earlier GPT-6 Astra entry ranks fifth at 1,393. The ratings refresh hourly and can change.
OpenAI president Greg Brockman shared the result on X under the line "GPT-6.2 for robotics", quoting a post that says the team ran hundreds of head to head comparisons in one day.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Robotics Brief or Daily AI Brief.
Also, consider following us on social media:
More from Robotics
Nov 20 Pragmatik Labs, founded by ex-Qwen lead Junyang Lin, reaches $5 billion valuation Nov 20 Auterion and SkyFall plan German factory to build drones for Ukraine Nov 20 John Deere acquires Orchard AI, maker of camera-based crop intelligence for growers Nov 19 Wallenberg Investments takes a stake in Swedish simulation company Algoryx Nov 19 Helsing scales back UK underwater drone plans after missing out on £90 million Royal Navy dealRobotics Brief
Weekly coverage of AI-driven robotics advances in industrial automation, autonomous vehicles, and robotic systems.
Humanoid Robot Makers
Companies building humanoid robots, from startups to Tesla and Boston Dynamics
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
OpenAI Tests GPT-6 Astra on Shopping and Meal Planning
OpenAI releases GPT-6.2 Astra and Sol, cutting Astra's API prices by 20%
New coding benchmark puts Claude Opus 5.5 on top and opens a 35-point gap that DeepSWE hid
Artificial Analysis Index v5: open-weight models fall 12 points behind
Epoch AI finds no model meets its employee standard, but Fable 5.2 matches contractors on data center research
Daily AI Brief: the AI news that matters, in your inbox.