Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Narrative Reasoning on Pororo (test)
Loading...
45
BLEURT Score
LogicAgent
39.8
41.15
42.5
43.85
Feb 7, 2026
BLEURT Score
Updated 4d ago
Evaluation Results
Method
Method
Links
BLEURT Score
LogicAgent
Number of Parameters=1...
2026.02
45
CEN
Model Type=Video Reaso...
2026.02
44.2
Qwen3-VL-8B
Model Type=Open-Source...
2026.02
44
GPT-4o
Model Type=Proprietary...
2026.02
43.9
Gemini 1.5 Pro
Model Type=Proprietary...
2026.02
43.9
NSVS-TL
Model Type=Video Reaso...
2026.02
43.9
Qwen2.5-VL-7B
Model Type=Open-Source...
2026.02
43.7
GIT
Model Type=Video Reaso...
2026.02
43.7
NS-DR
Model Type=Video Reaso...
2026.02
43.5
VideoLLaVA
Model Type=Open-Source...
2026.02
43.3
AKGNN
Model Type=Video Reaso...
2026.02
42.7
ShareGPT4Video
Model Type=Open-Source...
2026.02
42.3
SEM-POS
Model Type=Video Reaso...
2026.02
41.1
Vid2Seq
Model Type=Video Reaso...
2026.02
40
Feedback
Search any
task
Search any
task