Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text Generation on MVBench
Loading...
75.4
MVBench Score
V-JEPA 2.1 (+LLaMA3-8B)
30.784
42.367
53.95
65.533
Jun 29, 2026
MVBench Score
Updated 26d ago
Evaluation Results
Method
Method
Links
MVBench Score
V-JEPA 2.1 (+LLaMA3-8B)
Size (B)=10
2026.06
75.4
Qwen3.5
Size (B)=4
2026.06
67.1
Orca
Size (B)=4
2026.06
65.3
Orca
Size (B)=0.8
2026.06
53.6
Qwen3.5
Size (B)=0.8
2026.06
52.7
SmolVLM2
Size (B)=2
2026.06
48.7
Gemma 4
Size (B)=4
2026.06
45.6
MiniCPM-V-4.6
Size (B)=2
2026.06
41.4
DeepSeek-VL2
Size (B)=3
2026.06
40.5
Emu3.5
Size (B)=34
2026.06
39.5
Emu3
Size (B)=8
2026.06
35.2
Gemma 4
Size (B)=2
2026.06
32.5
Feedback
Search any
task
Search any
task