OpenAI
GPT-Image-2
Proprietary – cloud only
Benchmarks
Benchmark average
100/100
based on 2 benchmarks
| Benchmark | Score | Position | Source |
|---|---|---|---|
| LMArena Text-to-Image image generation | 1,382 Elo | 100/ 37 | LMArena · Nov 12, 2026 |
| LMArena Image Edit image generation | 1,462 Elo | 100/ 27 | LMArena · Nov 12, 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
- +Strong in image generation (position 100/100)
Cons
Our quality rating
Creating images3/3
Editing photos3/3
Tiers derived from: LMArena Text-to-Image 2026-11-12 · LMArena Image Edit 2026-11-12