Artificial Analysis Ranks GPT 6.2 Astra Second on Its Intelligence Index, Behind Only Claude Fable 5.2
OpenAI’s release of GPT-6.2 Astra and GPT-6.2 Sol delivers the #2 model in the Artificial Analysis Intelligence Index and most of the Cost per Task Pareto frontier @OpenAI's GPT-6.2 Astra is priced at $8/$40, 20% below GPT-6 Astra, and cached input drops to $0.40 from $1.00 per million tokens. GPT-6.2 Sol pricing is unchanged from GPT-6.1 Sol, at $2/$10 per million input/output tokens. Key takeaways: ➤ Second in Intelligence Index: OpenAI now trails only Anthropic’s Claude Fable 5.2 in the Artificial Analysis Intelligence Index. GPT-6.2 Astra jumps 5 points from GPT-6 Astra, overtaking Gemini 4 Carbon (60) and Claude Opus 5.5 (59) at their top effort settings. GPT-6.2 Sol gains 2 points at 57, placing it on par with GPT-6 Astra at ~15% of the Cost per Task. ➤ Occupies most of cost and output token frontiers: OpenAI models now occupy most of the Cost per Task Pareto frontier, sharing the frontier with only Anthropic and Meta. OpenAI also dominates the Output Token per Task Pareto Frontier, with Claude Fable 5.2 being the only model from a non-OpenAI lab appearing on the frontier. ➤ Strengths in science and knowledge: OpenAI performs strongly in both of our key science-focused evaluations, leading Terminal-Bench-Science 0.1, covering agentic scientific research workflows, and placing second only to Claude Fable 5.2 in CritPt v2 (hard subset), covering physics reasoning. GPT-6.2 Astra performs below only Claude Fable 5.2 in factual knowledge as measured by AA-Omniscience v1.1 Accuracy, and in HLE-Diamond, a reasoning and knowledge benchmark. ➤ Leading in 3D and robotics: GPT-6.2 Astra leads AA-3D at 1318, with Claude Fable 5.2 at 1271 and GPT-6.2 Sol at 1259. This benchmark measures how well models build interactive 3D experiences, and is rated by human graders. GPT-6.2 also leads AA-Robotics v0.1, our research preview measuring how well language models can understand, plan, and act in the real world. GPT-6.2 Astra and GPT-6.2 Sol scored 79 and 78 respectively, ahead of Claude Fable 5.2 at 75. Our team is hard at work adding more difficult tasks, as OpenAI and Anthropic models can now perform the majority of basic tasks in this initial research preview. ➤ No improvement in Coding Agent Index: 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 (Codex harness at max effort). For Sol, the drop is driven by a 14-point drop in SWE-Atlas-QnA-AA, where the model is more likely than its predecessor to omit key facts in its responses. Cost efficiency however does place several effort levels of GPT-6.2 Astra and Sol on the Pareto frontier for Cost per Task.
Context
An independent benchmark places OpenAI's new model near the top on intelligence and cost per task, while showing no gain on coding agent tasks.
OpenAI launched GPT 6.2 Astra and GPT 6.2 Sol on Nov 17. Artificial Analysis runs an independent Intelligence Index that combines many evaluations, along with cost and token efficiency measures. Its post lists the new prices and results across science, knowledge, 3D, robotics and coding.
Deep dive
Artificial Analysis posted that OpenAI's release of GPT 6.2 Astra and GPT 6.2 Sol delivers the second ranked model on its Intelligence Index and most of its Cost per Task frontier. It says OpenAI now trails only Anthropic's Claude Fable 5.2 on the index.
According to the post, GPT 6.2 Astra gained 5 points over GPT 6 Astra, overtaking Gemini 4 Carbon at 60 and Claude Opus 5.5 at 59 at their top effort settings. GPT 6.2 Sol gained 2 points to 57, on par with GPT 6 Astra at about 15% of the cost per task. Astra is priced at $8 per million input tokens and $40 per million output tokens, 20% below GPT 6 Astra, with cached input cut to $0.40 from $1.00. Sol stays at $2 and $10.
The post says OpenAI leads Terminal Bench Science, places second to Claude Fable 5.2 on a hard physics reasoning set, and leads both its 3D benchmark and a robotics research preview. It also reports no improvement on its Coding Agent Index: Astra is flat with GPT 6 Astra, and Sol loses 3 points versus GPT 6.1 Sol, driven by a 14 point drop on a question answering subset where the model omits key facts more often.
Theo, a developer and streamer, replied that Opus 5.5 is no longer on the value frontier by this measure but argued it remains the best value for long running coding work.
What to expect next
Other independent leaderboards, such as Arena and coding agent tests, will show whether these rankings hold up across different methods. Developers will watch whether the coding regression for Sol is fixed in a later update, and whether Anthropic or Google respond with price cuts or new models. Comments from OpenAI staff suggest early tester impressions came from an older build, so later evaluations may differ from the first wave of reviews.
