OpenAI's GPT-6.2 Astra Gains Coding Strength but Loses Chat Ground
Arena.ai's Agent Arena Index places OpenAI's GPT-6.2 Astra (Max) at #6 overall, just one spot above GPT-6 Astra (Max). The new model improves coding from 1,288 to 1,338, rising from #8 to #3, but drops in chat from 1,265 to 1,211, falling from #8 to #11, with the two shifts nearly canceling out in the aggregate score.
Related Entities
Full Report
Arena.ai (@arena) · 2026-11-21 17
GPT-6.2 Astra (Max) by @OpenAI ranks #6 on the Agent Arena Index, one place above GPT-6 Astra (Max). However, these models excel in very different capabilities. Let’s dive in by index.
GPT-6.2 Astra vs GPT-6 Astra across key Agent Arena Indexes:
- Coding: 1,338 vs 1,288 (+50)
- Work: 1,280 vs 1,267 (+13)
- Chat: 1,211 vs 1,265 (-54)
This shows the new model’s gain is in coding, where GPT-6.2 Astra climbs from #8 to #3. On Chat, the everyday tasks such as research, tutoring or writing, it drops from #8 to #11. The two shifts nearly cancel out in the overall score.
