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:
- GPT-6.2 Astra (Max): #6 with 1291 pts, now OpenAI's best model (+9 over GPT-6 Astra), with median cost per task down 40% ($2.94 vs $4.91); ranks #5 in Praise vs Complaint user satisfaction (1462 pts).
- GPT-6.2 Sol (Max): #11 with 1241 pts, tying GPT-6.1 Sol at 13% lower cost ($0.90 vs $1.04).
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.
More from Models
- Resolve launches SRE-1, a 27B RL-trained model for root-causing production incidents — tianyin_xu · 2026-11-19
- Theo does a about-face: 'Gemini 4 Neon might actually be a good model' — vitaliychiley · 2026-11-19
- Artificial Analysis Launches AA-PersonalityBench: 30 Traits, 8 Indexes, 53 Models — ArtificialAnlys · 2026-11-19
- GPT-6.2 writes 40% shorter, less structured replies and admits uncertainty far less, finds Artificial Analysis — ArtificialAnlys · 2026-11-19
- DeepSeek 4.1-Flash slips into game roles easily while Nemotron models need heavy coaxing — rickasaurus · 2026-11-19
- Leaked "Claude Mythos 5.5" strings spotted on Anthropic's site ahead of possible launch — imjustnewatai · 2026-11-19