Decision support
Nano Banana Pro (Gemini 3 Pro Image Preview) vs GPT Image 2.6 Sunburst
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
Benchmark results
Head to head on 2 benchmarks both models report
- Nano Banana Pro (Gemini 3 Pro Image Preview)0leads
- GPT Image 2.6 Sunburst2leads
Arena Text to Image
Arena rating · Higher is better
- Nano Banana Pro (Gemini 3 Pro Image Preview)1231Arena #20CI 1226 to 1236
- GPT Image 2.6 SunburstBest1406+175 ahead · Arena #2CI 1393 to 1419
Runs and sources
Nano Banana Pro (Gemini 3 Pro Image Preview)- default123195% CI 1226 to 1236 · 83,834 votes
GPT Image 2.6 Sunburst- medium140695% CI 1393 to 1419 · 2,718 votes
Arena Image Edit
Arena rating · Higher is better
- Nano Banana Pro (Gemini 3 Pro Image Preview)1385Arena #19CI 1382 to 1388
- GPT Image 2.6 SunburstBest1477+92 ahead · Arena #3CI 1466 to 1487
Runs and sources
Nano Banana Pro (Gemini 3 Pro Image Preview)- default138595% CI 1382 to 1388 · 533,223 votes
GPT Image 2.6 Sunburst- medium147795% CI 1466 to 1487 · 3,520 votes
Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.
Model specifications
API pricing · USD per 1M tokens
Capabilities and modalities
Architecture and availability
A dash means the field is not reported. Provider-specific performance and pricing may differ.