Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Out-of-scope Refusal Evaluation on MMMU (out-of-scope test)
Loading...
0.18
Refusal Rate
Prompt-based
0.1482
0.36285
0.5775
0.79215
Jan 31, 2026
Refusal Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Refusal Rate
Prompt-based
Subject=Math, Model ba...
2026.01
0.18
Persona
Subject=Math, Model ba...
2026.01
0.31
CR-VLM
Subject=Geography, Mod...
2026.01
0.81
Fine-tuning
Subject=Math, Model ba...
2026.01
0.885
CR-VLM
Subject=Math, Model ba...
2026.01
0.92
CR-VLM
Subject=Geography, Mod...
2026.01
0.93
CR-VLM
Subject=Art Theory, Mo...
2026.01
0.965
CR-VLM
Subject=Math, Model ba...
2026.01
0.97
CR-VLM
Subject=Art Theory, Mo...
2026.01
0.975
Feedback
Search any
task
Search any
task