A Very Big Video Reasoning Suite

We bet on a future that video reasoning is the next fundamental intelligence paradigm, after language reasoning, where spatiotemporal embodied world experiences could be more naturally captured.

Data Engines

View All
locate_twelve_o_clock_arrows
GitHub
Knowledge training set
The image contains 3 clocks, each with only an hour hand. Exactly one clock has its hour hand pointing to 12 o'clock. First find the single clock pointing to 12 o'clock, then draw a red circle around it. Do not change anything else. Show the complete solution step by step.
First Frame
Last Frame
raven
GitHub
Abstraction out-of-domain testset
This is Raven's Progressive Matrices like task. Complete the missing pattern in this 3x3 matrix.
First Frame
Last Frame
visual_jenga
GitHub
Spatiality training set
The scene shows objects stacked vertically. Extract the objects one by one from top to bottom in order, moving each object out of the frame before extracting the next one. Continue until all objects have been removed from the frame.
First Frame
Last Frame
shape_sorter
GitHub
Transformation out-of-domain testset
Solve the shape sorter puzzle exactly as shown. Move each colored shape card from the left staging area into its matching outline on the right. Keep the camera fixed in a top-down view throughout. Move only one card at a time, sliding each card smoothly without teleportation. Match the blue triangle, cyan square, and finally the purple star card. Continue until every outline is filled with its matching colored shape.
First Frame
Last Frame
mark_asymmetrical_shape
GitHub
Perception out-of-domain testset
Among the displayed shapes, exactly one is asymmetrical. Identify and circle that asymmetrical shape with a red circle. Do not change anything else.
First Frame
Last Frame

Inference Results

View Full Bench
Domino Chain Prediction - Samples
00
01
02
03
04
Task Domains 1/5
Domino Chain Prediction
Knowledge in-domain testset
Predict Next Color
Abstraction in-domain testset
Grid Number Sequence
Spatiality in-domain testset
Rolling Ball
Transformation in-domain testset
Multi Object Placement
Perception in-domain testset
Prompt
Loading...
Ground Truth
First
First Frame
Final
Final Frame
Model Outputs
1/
VBVR-Wan2.2
VBVR-Wan2.2
CogVideoX 1.5
Kling 2.6
LTX-2
Runway Gen-4
Sora 2
Veo 3
Wan 2.2 I2V
Hunyuan I2V
Seedance 2.0

Leaderboard

Modality
Split
Type
Category
2026-04-28