image model comparison
GPT Image 2.5 Sunburst vs Nano Banana 2.1
GPT Image 2.5 Sunburst and Nano Banana 2.1 are both current image models, from OpenAI and Google. On Arena Text-to-Image, GPT Image 2.5 Sunburst scores 1425 Elo and Nano Banana 2.1 1328 Elo (Arena, measured October 7, 2026).
Data verified October 12, 2026 · Dataset 2026-10-12
Side by side
Standard-tier prices in effect today. The better value in each row is highlighted.
| Fact | GPT Image 2.5 Sunburst | Nano Banana 2.1 |
|---|---|---|
| Price per image | Not reported | $0.0336 |
| Price per 1M input tokens | $5 | Not reported |
| Arena Text-to-Image | 1425 Elo (#1 of 9) (better) | 1328 Elo (#4 of 9) |
| Arena Image Edit | 1524 Elo (#1 of 8) (better) | 1428 Elo (#4 of 8) |
| Provider | OpenAI | |
| Release date | September 8, 2026 | October 6, 2026 |
| Access | API only | API only |
| Context window | Not reported | Not reported |
| Max output | Not reported | Not reported |
| Input | text, image | text, image, video |
| Output | image | image, text |
Scores:Arena · 2026-10-12
When to choose each
GPT Image 2.5 Sunburst
Best for
- Hero imagery, detailed edits and text-heavy graphics where quality matters most
Watch out for
- OpenAI publishes no per-image price, and its GPT Image 2 calculator does not estimate 2.5 token use, so cost per image has to be measured
- No independent image-quality benchmark is recorded here
Nano Banana 2.1
Best for
- High-volume product, marketing and social imagery where cost per image matters
- Iterative editing that must keep characters and objects consistent across turns
Watch out for
- Google prices output by image tokens; the per-image figures are Google's own equivalents and batch is half price
- No independent image-quality benchmark is recorded here
GPT Image 2.5 Sunburst vs Nano Banana 2.1 FAQ
Which scores higher on independent benchmarks, GPT Image 2.5 Sunburst or Nano Banana 2.1?
GPT Image 2.5 Sunburst leads on Arena Text-to-Image, 1425 Elo to 1328 Elo; GPT Image 2.5 Sunburst leads on Arena Image Edit, 1524 Elo to 1428 Elo. Scores are independent evaluations, not either vendor's launch figures.
Related comparisons
- FLUX1.1 [pro] vs GPT Image 2.5 Sunburst
- FLUX1.1 [pro] vs Nano Banana 2.1
- Gemini 3.1 Flash Image vs Nano Banana 2.1
- Gemini 3.1 Flash Lite Image vs Nano Banana 2.1
- Gemini 3 Pro Image vs GPT Image 2.5 Sunburst
- Gemini 3 Pro Image vs Nano Banana 2.1
- GPT Image 2.5 Flare vs GPT Image 2.5 Sunburst
- GPT Image 2.5 Flare vs Nano Banana 2.1
- GPT Image 2 vs GPT Image 2.5 Sunburst
- grok-imagine-image vs Nano Banana 2.1
Production evaluation
Choosing between GPT Image 2.5 Sunburst and Nano Banana 2.1?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty