Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Hallucination on MMVP
Loading...
72.1
Accuracy
Qwen2.5-VL
58.684
62.167
65.65
69.133
Feb 10, 2026
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-VL
Size=72B
2026.02
72.1
Visual Para-Thinker
Size=7B
2026.02
71.3
Gemini2.5-Pro
Size=-
2026.02
69.8
Majority voting@4
Size=7B
2026.02
68.9
Sequential
Size=7B
2026.02
68.7
Qwen2.5-VL
Size=7B
2026.02
68.3
GPT5-mini
Size=-
2026.02
65.3
Claude-4-Sonnet
Size=-
2026.02
63.9
GPT-4o
Size=-
2026.02
63.8
Visual Para-Thinker
Size=3B
2026.02
63.6
Majority voting@4
Size=3B
2026.02
60.1
Sequential
Size=3B
2026.02
60
Qwen2.5-VL
Size=3B
2026.02
59.2
Feedback
Search any
task
Search any
task