#GPT-6 Luna

3 articles with this tag

Messy bench data is the real AI test

OpenAI and Ligo grade agents on raw bench data. Astra jumps to 66.7% but still misreads controls.

Terminal X says its Eval Agent on GPT-6.1 Sol matched senior reviewers 88.6% vs 86.4% next-best, catching 25% more mandate drift at 30% lower cost.

OpenAI launched GPT-6 Sol and Luna at 50% below GPT-5.6 promo pricing, adding faster, cheaper tiers beneath Astra with new caching gains.