Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Narrative Reasoning on VIST (test)
Loading...
0.456
BLEURT
LogicAgent
0.37696
0.39748
0.418
0.43852
Feb 7, 2026
BLEURT
Updated 4d ago
Evaluation Results
Method
Method
Links
BLEURT
LogicAgent
Number of Parameters=1...
2026.02
0.456
Qwen3-VL-8B
Model Type=Open-Source...
2026.02
0.448
GPT-4o
Model Type=Proprietary...
2026.02
0.446
Gemini 1.5 Pro
Model Type=Proprietary...
2026.02
0.444
NSVS-TL
Model Type=Video Reaso...
2026.02
0.442
NS-DR
Model Type=Video Reaso...
2026.02
0.439
Qwen2.5-VL-7B
Model Type=Open-Source...
2026.02
0.433
CEN
Model Type=Video Reaso...
2026.02
0.433
AKGNN
Model Type=Video Reaso...
2026.02
0.428
GIT
Model Type=Video Reaso...
2026.02
0.426
ShareGPT4Video
Model Type=Open-Source...
2026.02
0.412
Vid2Seq
Model Type=Video Reaso...
2026.02
0.409
SEM-POS
Model Type=Video Reaso...
2026.02
0.385
VideoLLaVA
Model Type=Open-Source...
2026.02
0.38
Feedback
Search any
task
Search any
task