Sign in

Is GPT-6.2 Astra SOTA in Coding?Not enough data#32 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD

How it scores here

GPT-6.2 Astra in Coding

Primary benchmarks

  • LMArena Text (style-controlled, coding): 1523 (CI 1495–1550) on Nov 19, 2026 (#37 of 260).
Standings

Coding

#ModelState
1Claude Sonnet 5.5Co-SOTA
1Claude Opus 5.5Co-SOTA
1Kimi K3.1 ProCo-SOTA
2Claude Fable 5.2Near-SOTA
3GPT-6 AstraNear-SOTA
4GPT-6.1 Sol#4 in this category
5Claude Fable 5.1#5 in this category
6Claude Opus 5#6 in this category
7Gemini 4 Argon#7 in this category
8GPT-6.1 Terra#8 in this category
9GPT-6 Sol#9 in this category
10Muse Wonder#10 in this category

Category page →