aiqbench analysis
OpenAI's GPT-6.2 models deliver significant cost reductions, with Sol matching previous efficiency benchmarks while Astra achieves high intelligence scores at a fraction of the price. However, early evaluations reveal noticeable reinforcement learning artifacts in Astra that may impact reliability for specific workloads despite its competitive positioning against Anthropic.
[AINews] GPT-6.2 Astra, the #2 Frontier Model is better and 20%-600% cheaper, but has mixed reviews; 6.2 Sol likely main workhorse

From Latent Space
ExcerptNovember 17, 2026 — GPT-6.2 Astra and Sol lower benchmark costs. Early testers disagree on what Astra is like to work with.
OpenAI shipped GPT-6.2 Astra and Sol today, two days before Anthropic’s expected first trading day. In Artificial Analysis’ tests, Sol ties September’s Astra at about 15% of the cost per task. New Astra scores 62 on the Intelligence Index, just behind Fable 5.2 at 65. Net net, Anthropic still owns the world’s best model, but OpenAI owns the world’s most efficient models in terms of intelligence per $.
We think that some of this is overreacting and normal influencer tendency to either have everything be 🤯🤯🤯 or the literal WORST.MODEL.EVER, BUT also that some of the criticisms are valid, and the RL artefacts are noticeable and downright bizarre (don’t even get us started about the terrible launch video).
Excerpt shown under the publisher's RSS terms · 140 words · full text and figures are on the publisher's site
Other coverage of this story
- Latent Space · this article
- Epoch AI · How good are Fable 5.2 and GPT-6.2 Astra at real work?
- LiteLLM Blog · GPT-6.2 Astra and GPT-6.2 Sol API Pricing and Day 0 Support on LiteLLM
- OpenAI · Introducing GPT-6.2 Astra and Sol
- MarkTechPost · OpenAI Releases GPT-6.2 Astra and Sol With a 20% Cheaper Astra API
- VentureBeat · 'Essentially unusable': OpenAI launches GPT-6.2 Astra and Sol to negative reception from AI power users
and 3 more publishers
Related coverage

GPT-5.6 Is Here: Sol, Terra, and Luna
Analytics Vidhya · Jul 10, 2026

NVIDIA Nemotron 3.5 Lightning: The AI Agent Workhorse
Analytics Vidhya · Aug 14, 2026

Claude Opus 5: Near-Frontier Intelligence, On a Dial
Analytics Vidhya · Jul 27, 2026

Together Compiler: Continual Compilation for AI inference
Together AI · Nov 4, 2026