Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction-guided image editing preference prediction on GenAI-Bench
Loading...
65.72
Accuracy
EDITREWARD
24.3072
35.0586
45.81
56.5614
Sep 30, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
EDITREWARD
Backbone=MiMo-VL-7B-SFT
2025.09
65.72
EDITREWARD
Backbone=Qwen2.5-VL-7B
2025.09
63.97
ADIEE
Method Category=Open-S...
2025.09
59.96
GPT-5
Method Category=Propri...
2025.09
59.61
MiMo-VL-7B-SFT-2508
Method Category=Open-S...
2025.09
57.89
Gemini-2.5-Flash
Method Category=Propri...
2025.09
57.01
GPT-4o
Method Category=Propri...
2025.09
53.54
Gemini-2.0-Flash
Method Category=Propri...
2025.09
53.32
Qwen2.5-VL-3B-Inst
Method Category=Open-S...
2025.09
42.76
Qwen2.5-VL-7B-Inst
Method Category=Open-S...
2025.09
40.48
Qwen2.5-VL-32B-Inst
Method Category=Open-S...
2025.09
39.28
Random
Method Category=Baseline
2025.09
25.9
Feedback
Search any
task
Search any
task