Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context Video Understanding on VideoMME (test)
Loading...
69.3
Score
Qwen3-VL-4B
57.86
60.83
63.8
66.77
Mar 18, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Qwen3-VL-4B
Model=Qwen3-VL-4B, Pru...
2026.03
69.3
InternVL3.5-8B
Model=InternVL3.5-8B,...
2026.03
66
STTS
Model=STTS, Pruning St...
2026.03
63.4
Baseline
Model=Baseline, Prunin...
2026.03
62.8
STTS
Model=STTS, Pruning St...
2026.03
62.4
STTS
Model=STTS, Pruning St...
2026.03
62.4
PLM-8B
Model=PLM-8B, Pruning...
2026.03
58.3
Feedback
Search any
task
Search any
task