Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Preference Agreement on MM-RewardBench2 Edit
Loading...
79.2
Accuracy
Gemini 3.1 Pro + ARR
58.4
63.8
69.2
74.6
May 8, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini 3.1 Pro + ARR
Model Category=ARR (Ou...
2026.05
79.2
GPT-5 + ARR
Model Category=ARR (Ou...
2026.05
77.5
Gemini 3.1 Pro
Model Category=VLM-as-...
2026.05
77.4
GPT-5
Model Category=VLM-as-...
2026.05
73.8
EditReward
Model Category=Trained...
2026.05
67.2
Qwen3vl-8B + ARR
Model Category=ARR (Ou...
2026.05
65.5
Qwen3-VL-8B
Model Category=VLM-as-...
2026.05
59.2
Feedback
Search any
task
Search any
task