GPT-6.2 Astra gains +50 in coding, drops -54 in chat on Agent Arena
arena · x · 2026-11-22
Arena reports GPT-6.2 Astra (Max) ranks #6 on the Agent Arena Index, just one spot above GPT-6 Astra (Max), but the two models differ sharply by capability:
- Coding: 1338 vs 1288 (+50), climbing from #8 to #3
- Work: 1280 vs 1267 (+13)
- Chat: 1211 vs 1265 (-54), falling from #8 to #11
The takeaway: the new model regresses on everyday tasks like research, tutoring and writing, and its coding gain is nearly canceled out by the chat decline in the overall score.
More from Models
- GPT-6.2 Astra writing success rate falls to 85.9% from 91.2% — arena · 2026-11-22
- Apple testing daily limits on advanced Siri AI requests in iOS 27.3 beta, per leak — alvelda · 2026-11-22
- Muse plays GTA6, suggesting guardrails don't cover game playing — Dave_Maynor · 2026-11-22
- Paying Google Workspace users locked out of Gemini over custom-domain account restrictions — film_girl · 2026-11-22
- Lean Community Verifies 17M Lines of Code, Confirms Claude-Assisted Riemann Hypothesis Proof — Polymarket · 2026-11-22
- Claude predicts AI will crack math proofs, battery materials and abandoned drug candidates within 5 years — alex_verem · 2026-11-22