Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Alignment on MIA-Bench
Loading...
93.3
Accuracy
EVE (Ours-8B-iter4)
89.764
90.682
91.6
92.518
Apr 20, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
EVE (Ours-8B-iter4)
Model Category=Pseudo-...
2026.04
93.3
VisPlay-8B-iter3
Model Category=Pseudo-...
2026.04
93
MM-Zero-8B-iter3
Model Category=Pseudo-...
2026.04
92.9
GPT-5 mini (minimal)
Model Category=Closed-...
2026.04
92.3
Qwen3-VL-8B-Instruct
Model Category=Open-So...
2026.04
92
Jigsaw-R1-8B
Model Category=Templat...
2026.04
91.3
GPT-5 nano (high)
Model Category=Closed-...
2026.04
89.9
Feedback
Search any
task
Search any
task