Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-reference image generation on User Study 50 samples
Loading...
8.5
Subjective Score
Nano Pro
0.9184
2.8867
4.855
6.8233
Jun 25, 2026
Subjective Score
PLCC
SROCC
KROCC
Mean Kendall's W
Updated 29d ago
Evaluation Results
Method
Method
Links
Subjective Score
PLCC
SROCC
KROCC
Mean Kendall's W
Nano Pro
Evaluation Setup=Gemin...
2026.06
8.5
0.89
0.8
0.67
0.78
DyRef
Evaluation Setup=Gemin...
2026.06
8.38
0.89
0.8
0.67
0.78
Seedream 4.5
Evaluation Setup=Gemin...
2026.06
8.13
0.89
0.8
0.67
0.78
Qwen-2511
Evaluation Setup=Gemin...
2026.06
4.97
0.89
0.8
0.67
0.78
DyRef
Evaluation Setup=Human
2026.06
3.53
-
-
-
-
Nano Pro
Evaluation Setup=Human
2026.06
2.96
-
-
-
-
Seedream 4.5
Evaluation Setup=Human
2026.06
2.3
-
-
-
-
Qwen-2511
Evaluation Setup=Human
2026.06
1.21
-
-
-
-
Feedback
Search any
task
Search any
task