XNews

OpenAI Releases GPT-6.2 Astra and Sol, Ranking Second in Intelligence Index

OpenAI Releases GPT-6.2 Astra and Sol, Ranking Second in Intelligence Index

OpenAI released GPT-6.2 Astra and GPT-6.2 Sol, with Astra priced at $8/$40 per million tokens, 20% below GPT-6 Astra, and Sol unchanged at $2/$10. Astra ranks second in the Artificial Analysis Intelligence Index behind Claude Fable 5.2, while OpenAI models occupy most of the Cost per Task Pareto frontier. GPT-6.2 leads AA-3D and AA-Robotics benchmarks, but shows no improvement in the Coding Agent Index.

Event version 1.

Key insights

Second in Intelligence Index

GPT-6.2 Astra ranks second in the Artificial Analysis Intelligence Index, trailing only Anthropic's Claude Fable 5.2. Astra jumps 5 points from GPT-6 Astra, overtaking Gemini 4 Carbon (60) and Claude Opus 5.5 (59). GPT-6.2 Sol gains 2 points at 57, placing it on par with GPT-6 Astra at ~15% of the Cost per Task.

Cost and Output Token Frontiers

OpenAI models occupy most of the Cost per Task Pareto frontier, sharing it with only Anthropic and Meta. OpenAI also dominates the Output Token per Task Pareto Frontier, with Claude Fable 5.2 the only non-OpenAI model on the frontier.

Science and Knowledge Strengths

OpenAI leads Terminal-Bench-Science 0.1 and places second only to Claude Fable 5.2 in CritPt v2 (hard subset). GPT-6.2 Astra performs below only Claude Fable 5.2 in AA-Omniscience v1.1 Accuracy and in HLE-Diamond.

3D and Robotics Leadership

GPT-6.2 Astra leads AA-3D at 1318, with Claude Fable 5.2 at 1271 and GPT-6.2 Sol at 1259. GPT-6.2 Astra and Sol score 79 and 78 in AA-Robotics v0.1, ahead of Claude Fable 5.2 at 75.

No Coding Agent Index Improvement

GPT-6.2 Astra is flat with GPT-6 Astra and GPT-6.2 Sol loses 3 points relative to GPT-6.1 Sol in the Artificial Analysis Coding Agent Index. For Sol, the drop is driven by a 14-point drop in SWE-Atlas-QnA-AA.

Source posts