Skip to main content
Image model

HunyuanImage 3.0 Instruct

Tencent

Released
January 2026
Data date
August 15, 2026
Parameters
Benchmark configuration
Price
Per image

HunyuanImage 3.0 Instruct can rewrite prompts and use CoT Think in addition to text-to-image and text-image-to-image. The instruction-tuned open-weight variant has 80B total and 13B active parameters and targets precise instructions, layout, and iterative editing.

Tencent recommends at least eight GPUs with 80GB each for the Instruct variant. Base, Instruct, and distilled variants are separate checkpoints and should not be treated as interchangeable.

Position
Rank 12 of 30
Index score
55.8 / 100
1.Krea 2 Large75.6 / 100
2.GPT Image 274.2 / 100
5.Luma Uni-1.1 Max63.8 / 100
6.MAI-Image-2.561.8 / 100
8.Reve 2.160.1 / 100
9.Seedream 5.0 Pro57.2 / 100
11.GPT Image 2.5 Flare56.3 / 100
13.FLUX.2 Max55.8 / 100
14.Nano Banana Pro53.8 / 100
15.Nano Banana 2 Lite53.2 / 100
17.Nano Banana 251.1 / 100
18.FLUX.2 Flex49.4 / 100
19.GPT Image 1.548.3 / 100
20.Qwen Image 2.0 Pro47.7 / 100
21.FLUX.2 Pro46 / 100
23.Ideogram 4.045.4 / 100
25.Seedream 4.037.7 / 100
27.Midjourney V8.128.5 / 100
28.FLUX.2 Klein 9B24.4 / 100
29.HiDream-O1-Image19.3 / 100
Methodology and source

This position gives equal weight to 4 fixed Gradually image tests. One archived first output contributes for each model and task.