Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Content Description Quality on XM3600
Loading...
65.28
Preference Rate
LLaVA-PLLuM-12B-nc
44.9168
50.2034
55.49
60.7766
Feb 15, 2026
Preference Rate
Updated 3d ago
Evaluation Results
Method
Method
Links
Preference Rate
LLaVA-PLLuM-12B-nc
Judge Model=llava-onev...
2026.02
65.28
LLaVA-PLLuM-12B-nc-250715
Judge Model=llava-onev...
2026.02
64.83
LLaVA-Bielik-11B-v2.6
Judge Model=llava-onev...
2026.02
62.39
LLaVA-PLLuM-12B-nc
Judge Model=llava-onev...
2026.02
58.68
LLaVA-PLLuM-12B-nc-250715
Judge Model=llava-onev...
2026.02
57.38
LLaVA-Bielik-11B-v2.6
Judge Model=llava-onev...
2026.02
55.47
LLaVA-PLLuM-12B-nc
Judge Model=llava-onev...
2026.02
51.4
LLaVA-PLLuM-12B-nc-250715
Judge Model=llava-onev...
2026.02
49.76
LLaVA-PLLuM-12B-nc
Judge Model=llava-onev...
2026.02
49.29
LLaVA-PLLuM-12B-nc
Judge Model=llava-onev...
2026.02
48.75
LLaVA-Bielik-11B-v2.6
Judge Model=llava-onev...
2026.02
48.71
LLaVA-PLLuM-12B-nc-250715
Judge Model=llava-onev...
2026.02
47.38
LLaVA-Bielik-11B-v2.6
Judge Model=llava-onev...
2026.02
46.72
LLaVA-PLLuM-12B-nc-250715
Judge Model=llava-onev...
2026.02
46.69
LLaVA-Bielik-11B-v2.6
Judge Model=llava-onev...
2026.02
45.7
Feedback
Search any
task
Search any
task