Share your thoughts, 1 month free Claude Pro on usSee more

Video Reasoning on VBVR-Bench Out-of-Domain

0.988Average Score

Human

Updated 1mo ago

Evaluation Results

Method	Links
Human 2026.03		0.988	1	1	0.99	1	0.97
VBVR-Wan2.2 + Training-Free Ensemble 2026.03		0.65	0.803	0.705	0.531	0.639	0.716
VBVR-Wan2.2 2026.03		0.61	0.768	0.572	0.547	0.618	0.615
Sora 2 2026.03		0.523	0.546	0.472	0.525	0.462	0.546
Veo 3.1 2026.03		0.429	0.577	0.277	0.42	0.441	0.404
Runway Gen-4 Turbo 2026.03		0.414	0.515	0.429	0.419	0.327	0.373
Kling 2.6 2026.03		0.33	0.528	0.135	0.272	0.356	0.359
Wan2.2-I2V-A14B 2026.03		0.329	0.405	0.308	0.343	0.236	0.307
LTX-2 2026.03		0.297	0.244	0.337	0.317	0.231	0.311
HunyuanVideo-I2V 2026.03		0.265	0.175	0.369	0.29	0.253	0.25
CogVideoX1.5-5B-I2V 2026.03		0.262	0.281	0.235	0.25	0.254	0.282