OpenAI
GPT-5.2-Codex
Proprietary – cloud only
Benchmarks
Benchmark average
11/100
based on 1 benchmarks
| Benchmark | Score | Position | Source |
|---|---|---|---|
| LMArena WebDev coding | 1,339 Elo | 11/ 108 | LMArena · Nov 15, 2026 |
Position: 100 = best, 0 = last among all models listed here that were tested on this benchmark.
Strengths & weaknesses
Automatic summary from benchmark positions – not an opinion.
Pros
Cons
- −Weaker in coding (position 11/100)
Our quality rating
Programming1/3
Tiers derived from: LMArena WebDev 2026-11-15