Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long Video Reasoning on LongVideoReason (eval)
Loading...
80.3
Accuracy
VideoZoomer
58.46
64.13
69.8
75.47
Oct 23, 2025
Nov 24, 2025
Dec 27, 2025
Jan 29, 2026
Mar 2, 2026
Apr 4, 2026
May 7, 2026
Accuracy
Updated 26d ago
Evaluation Results
Method
Method
Links
Accuracy
VideoZoomer
Size=7B, Evaluation Pr...
2025.12
80.3
LongVT-RL-7B
Category=Tool-calling...
2026.05
75.1
VISD
Category=Ours
2026.05
73.5
Video-R1
Size=7B, Evaluation Pr...
2025.12
72.8
Qwen2.5-VL
Size=7B, Evaluation Pr...
2025.12
70.8
VisionCoach-7B
Category=Tool-free Met...
2026.05
70.7
VideoRFT-7B
Model=VideoRFT-7B
2025.10
69.4
Open-o3-Video-7B (Ours)
Model=Open-o3-Video-7B...
2025.10
69.4
VideoRFT-7B
Category=Tool-free Met...
2026.05
69.4
Open-o3-Video-7B
Category=Tool-free Met...
2026.05
69.1
VideoR1-7B
Model=VideoR1-7B
2025.10
68.9
VideoR1-7B
Category=Tool-free Met...
2026.05
68.9
LongVILA-R1
Size=7B, Evaluation Pr...
2025.12
67.9
Gemini-1.5-Pro
Size=-, Evaluation Pro...
2025.12
67.3
GPT-4o
Category=Proprietary M...
2026.05
66
InternVL-2.5-8B
Model=InternVL-2.5-8B
2025.10
62
GPT-4o
Size=-, Evaluation Pro...
2025.12
60.7
VideoLLaMA3-7B
Model=VideoLLaMA3-7B
2025.10
59.8
Qwen2.5-VL-7B (Base)
Model=Qwen2.5-VL-7B (B...
2025.10
59.3
Qwen2.5-VL-7B
Category=Tool-free Met...
2026.05
59.3
Feedback
Search any
task
Search any
task