Share your thoughts, 1 month free Claude Pro on us
See more
Feedback
Search any
task
Search any
task
SOTA Long Video Question Answering benchmarks and papers with code | Wizwand
Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Tasks
Long Video Question Answering
Benchmarks
Dataset Name
SOTA Method
Dataset Name
SOTA Method
Metric
Trend
Results
Last Updated
MLVU
InternVL-3-78B
M-Avg
79.5
39
2mo ago
Long VideoBench (val)
GPT-5
Accuracy
72.6
36
3mo ago
Video-MME
ToolMerge
Accuracy
73.2
30
9d ago
MovieChat-1K Breakpoint Mode (test)
HierarQ
Accuracy
76.4
24
3mo ago
MovieChat-1K Global Mode (test)
HierarQ
Accuracy
87.5
24
3mo ago
LV-Bench (val)
Video-RAG
Overall Accuracy
66.4
20
1mo ago
EgoSchema (full set)
Dispider
Accuracy
55.6
17
3mo ago
LVBench
Qwen3-VL
All Score
58
16
15d ago
Video-MME Long without Subtitles
Video-RAG
Overall Accuracy
62.3
16
1mo ago
Video-MME w/o subtitles
GPT-5
Accuracy
0.818
14
3mo ago
Video-MME (val)
Gemini-1.5-Pro
Accuracy
75
12
3mo ago
MLVU multiple-choice questions
VideoXL
Accuracy
0.649
12
3mo ago
MLVU 3–120 min
Qwen2.5-VL-7B
Accuracy
66.9
11
2mo ago
MMBench-Video (val)
InternVL2.5-78B
Score
1.97
11
3mo ago
VideoMME long 30–60 min
WAT
Accuracy
50.8
10
2mo ago
TemporalBench
GPT-4o
Binary Accuracy
73.2
9
3mo ago
TVQA Long
LLaVA-Video + OneClip-RAG
Overall Accuracy
52.1
6
3mo ago
GLVC (test)
VideoDetective
Score
69
6
3mo ago
CASTLE Challenge CVPR 2026 EgoVis Workshop
WDL
Accuracy
58
5
1d ago
QaEgo4D
LLaVA-Video + OneClip-RAG
Score
1.71
5
3mo ago
Showing 20 of 20 rows
25 / page
50 / page
100 / page
1
Search any
task
Search any
task
Privacy Policy
Terms of Service
FAQs
Swarm Docs
