Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Success detection on ManiRewardBench
Loading...
0.826
ROC AUC
TOPReward
0.50672
0.58961
0.6725
0.75539
Feb 22, 2026
ROC AUC
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROC AUC
TOPReward
Model=Gemini-2.5-Pro
2026.02
0.826
GVL
Model=Gemini-2.5-Pro
2026.02
0.823
TOPReward
Model=Qwen3-VL-8B
2026.02
0.654
GVL
Model=Qwen3-VL-8B
2026.02
0.519
Feedback
Search any
task
Search any
task
