GPT-6.2 fails to beat GPT-6 on Coding Agent Index, trailing Claude and Gemini
realsohamparekh · x · 2026-11-18
- Per Artificial Analysis, GPT-6.2 Astra is flat with GPT-6 Astra (both 53) and GPT-6.2 Sol loses 3 points versus GPT-6.1 Sol on the Coding Agent Index (Codex harness, max effort).
- That makes this the first OpenAI launch trailing Google (Antigravity CLI + Gemini 4 Carbon, 55), Meta's Muse Code Wonder (54), and Anthropic's Claude Code with Fable 5.2 XHigh / Opus 5.5 Max, which lead at 58.
- Commenters found the regression notable for an OpenAI release.
More from Models
- GPT-6.2 Astra scores 100% on ARC-AGI-3, first model to max the benchmark — patience_cave · 2026-11-18
- Teknium flags inconsistent OpenAI demos: was GPT-6 quietly nerfed before GPT-6.2? — Teknium · 2026-11-18
- GPT-6.2 Astra beats Opus 5.5 across agent benchmarks at 3-6x lower cost — VraserX · 2026-11-18
- Side-by-side: GPT-6.2 Astra builds noticeably richer scenes than GPT-6 Astra — Angaisb_ · 2026-11-18
- 3 weeks with OpenAI Astra 5.2: shines at delegating under messy stacked context — round · 2026-11-18
- Perplexity hosts AMA on Decider V1.3 decision model, free on OpenRouter now — antoine_chaffin · 2026-11-18