GPT-6.2 Astra debuts #6 on new Agent Arena Index as OpenAI's best model, 40% cheaper per task

arena · x · 2026-11-19

Arena launched its new headline Agent Arena Index, built from millions of real-world community tasks. Based on 7.1K+ real agentic sessions:

On Code Arena WebDev, both land on the Pareto frontier: Astra #3 (1781 pts, cost down 42%, #1 in Consumer Product), Sol #7 (1757 pts, cost down 21%). The leaderboard image shows Claude Fable 5.2 (Max) on top at 1448 pts, with Anthropic and Google placing multiple models in the top 15.

Related event: LMArena Launches Agent Arena Index; GPT-6.2 Models Top Cost-Performance Frontier(3 posts)→

Original post →

More from Models

Models channel →