Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-modal Video Understanding on LongVideoBench (accuracy)
Loading...
47.9
Accuracy
InternVL2.5
43.116
44.358
45.6
46.842
Mar 26, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
InternVL2.5
Arch.=Dense, # activat...
2026.03
47.9
InternVL3.5 + Stoch-FT-Multi
Arch.=MoE, # activated...
2026.03
47
InternVL3.5 + MoE-GRPO (ours)
Arch.=MoE, # activated...
2026.03
46.5
LLaVA-OV
Arch.=Dense, # activat...
2026.03
45.8
InternVL3.5 + Det-FT
Arch.=MoE, # activated...
2026.03
45.3
InternVL3.5 + Stoch-FT-Noise
Arch.=MoE, # activated...
2026.03
45.3
InternVL2
Arch.=Dense, # activat...
2026.03
43.3
Feedback
Search any
task
Search any
task