GPT Image 2 vs Nano Banana 2.1
In image generation, GPT Image 2 scores 83.1 and Nano Banana 2.1 77.6 on the 0–100 quality scale. GPT Image 2 costs 6.3× as much as Nano Banana 2.1 ($0.21 vs $0.034 per image).
GPT Image 2Nano Banana 2.1
Image generation: quality vs price
Compared models are ringed; the other 42 ranked here are greyed.
Lower price is better. Pareto frontier: Z-Image Turbo, Muse Image, MAI-Image-2.6-Flash, Nano Banana 2.1, GPT Image 2.5 Sunburst. 2 models are not plotted: Qwen-Image-2.1, Ideogram 4.5.
2 models with no price data — shown in the strip at the left edge
Qwen-Image-2.1, Ideogram 4.5
- Best-value frontier (nothing is both cheaper and better)
- Evidencestrong → weak
- Estimated from other categories
- Hover a dot for details · click a lab to highlight it
- GPT Image 2
- Quality
- 83.1
- Rank
- #3/44
- Price
- $0.21/img
- Speed
- 118s
vs Nano Banana 2.1: +5.5 quality · 6.3× price
- Nano Banana 2.1
- Quality
- 77.6
- Rank
- #4/44
- Price
- $0.034/img
- Speed
- —
vs GPT Image 2: −5.5 quality · 0.16× price
Overview
Lab
OpenAI
Google DeepMind
Released
Apr 21, 2026
Oct 6, 2026
Weights
Proprietary
Proprietary
Price per image
$0.21
$0.034Best
Time per image
118s
—
Quality by category
0–100 within each category (100 = best tracked model). Rank is among all models ranked there. Click a row to focus it.
Image generation benchmarks
Rank among models with a published score, and the leaderboard around each model. ~ italic = no published score, estimated from related benchmarks.
AA Text-to-Image Arena
third-party
AA Image Editing Arena
third-party
#6/351130Verified
artificialanalysis.ai · 2026-10-13
LMArena Text-to-Image
third-party
#3/321381BestVerified
arena.ai · 2026-10-13
#6/321328Verified
arena.ai · 2026-10-06
LMArena Image Edit
third-party
#3/261461BestVerified
arena.ai · 2026-10-13
#6/261428Verified
arena.ai · 2026-10-06
GenEval
day 0
~#2/4~88.3%Estimated
estimated from related benchmarks
~#2/4~87.9%Estimated
estimated from related benchmarks
DPG-Bench
day 0
~#2/4~88.6%Estimated
estimated from related benchmarks
~#2/4~88.4%Estimated
estimated from related benchmarks