LMArena Launches Agent Arena Index; GPT-6.2 Models Top Cost-Performance Frontier
LMArena launched its Agent Arena Index built on millions of real community tasks. GPT-6.2 Astra (Max) ranked 6th as OpenAI's strongest model, while GPT-6.2 Sol (Max) reset the Pareto cost frontier at $0.90 per task with a score of 1241.
2026-11-19 ~ 2026-11-19 · 3 related posts
- GPT-6.2 Astra debuts #6 on new Agent Arena Index as OpenAI's best model, 40% cheaper per task — arena · 2026-11-19
- GPT-6.2 Sol reshapes Agent Arena Pareto frontier at $0.90 median cost per task — arena · 2026-11-19
1 near-duplicate retellings: arena