Rather
Rather
World model benchmarks
Video generation quality across 16 dimensions, including subject consistency, motion, visual quality and alignment with the prompt.
VBenchRather-generated AI video · Preview · Unscored
Does the swimmer stay consistent?
What to look for Track the same swimmer across frames: body shape, identity, water motion and continuity.
Generate the scene described below.
a person swimming in ocean
VBench 1.0 / subject consistency, dynamic degree, motion smoothness
Generated by Rather. An official benchmark input run with preview settings. No benchmark scores have been computed for these clips.
Case and seed 42 were fixed before generation. All 2 planned model outputs are shown; no best-of selection.
These exact checkpoints were run by Rather. They are not linked to similarly named source-reported leaderboard entries. Full prompts, model revisions, settings and output hashes are in each run record.
768 x 448 visual preview; not a full benchmark evaluation. One preselected seed per model; no output selection or prompt optimization. Conditioning images are resized to the full output frame without cropping. Generated MP4 streams are remuxed for playback; VP9 WebM copies are encoded at CRF 24 for browser compatibility with no frame interpolation. Original outputs remain linked. Reference footage, where provided, is resized to 768 pixels wide; source hashes and attribution are preserved. Input licenses are listed here; model licenses are linked in each run record.
VBench authors / Vchitect. Generation by Rather.
Wan 2.2 TI2V 5B · Seed 42 · 768 × 448 · 121 frames per turn · 24 fps · 40 steps · Guidance 5. Full run record & prompts (opens in a new tab)
LTX-Video 0.9.5 2B · Seed 42 · 768 × 448 · 121 frames per turn · 24 fps · 40 steps · Guidance 5. Full run record & prompts (opens in a new tab)
Source revision: fd18b3d055cb0fc6f066ca90fe2c3c8cbb698490
Link to this example ↗% · Higher is better · Published by VBench
| Compare | Model / variant | % | % | % | Evidence |
|---|---|---|---|---|---|
HiDream-O1-VideoText-to-videoNot specified by source | 89.74 | 89.43 | 90.99 | View source ↗Organizer evaluated | |
IPOWText-to-videoNot specified by source | 88.26 | 87.83 | 90.01 | View source ↗Organizer evaluated | |
Vidu Q1 (2025-04-17)Text-to-videoNot specified by source | 87.41 | 87.28 | 87.94 | View source ↗Organizer evaluated | |
IPOC (2025-04-14)Text-to-videoNot specified by source | 86.57 | 87.00 | 84.84 | View source ↗Organizer evaluated | |
JT3.5Text-to-videoNot specified by source | 86.47 | 87.04 | 84.19 | View source ↗Organizer evaluated | |
Wan2.1 (2025-02-24)Text-to-videoNot specified by source | 86.22 | 86.67 | 84.44 | View source ↗Organizer evaluated | |
IPOCText-to-videoNot specified by source | 85.71 | 86.12 | 84.09 | View source ↗Organizer evaluated | |
MiracleVision V5Text-to-videoNot specified by source | 85.23 | 86.68 | 79.43 | View source ↗Organizer evaluated | |
Veo 3Text-to-videoNot specified by source | 85.06 | 85.70 | 82.49 | View source ↗Organizer evaluated | |
LanDiffText-to-videoNot specified by source | 84.87 | 85.41 | 82.72 | View source ↗Organizer evaluated | |
Wan2.1Text-to-videoNot specified by source | 84.70 | 85.64 | 80.95 | View source ↗Organizer evaluated | |
Open-Sora-2.0 (2025-03-18)Text-to-videoNot specified by source | 84.34 | 85.40 | 80.12 | View source ↗Organizer evaluated | |
SoraText-to-videoNot specified by source | 84.28 | 85.51 | 79.35 | View source ↗Organizer evaluated | |
CausVid(2025-01-02 5s)Text-to-videoNot specified by source | 84.27 | 85.65 | 78.75 | View source ↗Organizer evaluated | |
Wan2.1-T2V-1.3BText-to-videoNot specified by source | 84.26 | 85.30 | 80.09 | View source ↗Organizer evaluated | |
Wan2.2-T2V-A14B (Qwen prompt-optimized)Text-to-videoNot specified by source | 84.23 | 85.42 | 79.50 | View source ↗Organizer evaluated | |
CausVidText-to-videoNot specified by source | 83.88 | 85.21 | 78.57 | View source ↗Organizer evaluated | |
Wan2.1-T2V-14BText-to-videoNot specified by source | 83.69 | 85.59 | 76.11 | View source ↗Organizer evaluated | |
LumaText-to-videoNot specified by source | 83.61 | 83.47 | 84.17 | View source ↗Organizer evaluated | |
Hunyuan Video (2025-05-22)Text-to-videoNot specified by source | 83.43 | 85.07 | 76.88 | View source ↗Organizer evaluated | |
EasyAnimateV5.1Text-to-videoNot specified by source | 83.42 | 85.03 | 77.01 | View source ↗Organizer evaluated | |
MiniMax-Video-01Text-to-videoNot specified by source | 83.41 | 84.85 | 77.65 | View source ↗Organizer evaluated | |
Kling 1.6Text-to-videoNot specified by source | 83.40 | 85.00 | 76.99 | View source ↗Organizer evaluated | |
STIV (Apple)Text-to-videoNot specified by source | 83.35 | 84.80 | 77.57 | View source ↗Organizer evaluated | |
Wan2.1-T2V-1.3B (2025-05-03)Text-to-videoNot specified by source | 83.31 | 85.23 | 75.65 | View source ↗Organizer evaluated | |
AccVideoText-to-videoNot specified by source | 83.28 | 84.58 | 78.06 | View source ↗Organizer evaluated | |
HunyuanVideo (Open-Source Version)Text-to-videoNot specified by source | 83.24 | 85.09 | 75.82 | View source ↗Organizer evaluated | |
Wan2.2-T2V-A14B (w/o prompt-optimized)Text-to-videoNot specified by source | 82.61 | 85.03 | 72.92 | View source ↗Organizer evaluated | |
Gen-3 (2024-07)Text-to-videoNot specified by source | 82.32 | 84.11 | 75.17 | View source ↗Organizer evaluated | |
Vchitect-2.0 (VEnhancer)Text-to-videoNot specified by source | 82.24 | 83.54 | 77.06 | View source ↗Organizer evaluated | |
CogVideoX1.5-5B (5s SAT prompt-optimized)Text-to-videoNot specified by source | 82.17 | 82.78 | 79.76 | View source ↗Organizer evaluated | |
CogVideoX1.5-5BText-to-videoNot specified by source | 82.01 | 82.72 | 79.17 | View source ↗Organizer evaluated | |
JimengText-to-videoNot specified by source | 81.97 | 83.29 | 76.69 | View source ↗Organizer evaluated | |
RepVideoText-to-videoNot specified by source | 81.94 | 82.70 | 78.91 | View source ↗Organizer evaluated | |
CogVideoX-5B (Diffusers)Text-to-videoNot specified by source | 81.91 | 83.05 | 77.33 | View source ↗Organizer evaluated | |
ViduText-to-videoNot specified by source | 81.89 | 83.85 | 74.04 | View source ↗Organizer evaluated | |
Kling (2024-07 high-performance mode)Text-to-videoNot specified by source | 81.85 | 83.39 | 75.68 | View source ↗Organizer evaluated | |
MAGI-T2V-24B-distillText-to-videoNot specified by source | 81.83 | 84.69 | 70.37 | View source ↗Organizer evaluated | |
Step-Video-T2VText-to-videoNot specified by source | 81.83 | 84.46 | 71.28 | View source ↗Organizer evaluated | |
Open-Sora-2.0Text-to-videoNot specified by source | 81.71 | 82.10 | 80.14 | View source ↗Organizer evaluated | |
CogVideoX-5B (SAT prompt-optimized)Text-to-videoNot specified by source | 81.61 | 82.75 | 77.04 | View source ↗Organizer evaluated | |
Vchitect-2.0-2BText-to-videoNot specified by source | 81.57 | 82.51 | 77.79 | View source ↗Organizer evaluated | |
CogVideoX-2B (Diffusers)Text-to-videoNot specified by source | 81.55 | 82.48 | 77.81 | View source ↗Organizer evaluated | |
CogVideoX-2B (SAT prompt-optimized)Text-to-videoNot specified by source | 80.91 | 82.18 | 75.83 | View source ↗Organizer evaluated | |
Pika-1.0 (2024-06)Text-to-videoNot specified by source | 80.69 | 82.92 | 71.77 | View source ↗Organizer evaluated | |
Gen-2 (2023-12)Text-to-videoNot specified by source | 80.58 | 82.47 | 73.03 | View source ↗Organizer evaluated | |
VideoCrafter-2.0Text-to-videoNot specified by source | 80.44 | 82.20 | 73.42 | View source ↗Organizer evaluated | |
Pika Beta (2023-12)Text-to-videoNot specified by source | 80.40 | 82.68 | 71.26 | View source ↗Organizer evaluated | |
AnimateDiff-V2Text-to-videoNot specified by source | 80.27 | 82.90 | 69.75 | View source ↗Organizer evaluated | |
Mochi-1Text-to-videoNot specified by source | 80.13 | 82.64 | 70.08 | View source ↗Organizer evaluated | |
LTX-Video (5s 768×512)Text-to-videoNot specified by source | 80.00 | 82.30 | 70.79 | View source ↗Organizer evaluated | |
OpenSora V1.2 (8s)Text-to-videoNot specified by source | 79.76 | 81.35 | 73.39 | View source ↗Organizer evaluated | |
VideoCrafter-1.0Text-to-videoNot specified by source | 79.72 | 81.59 | 72.22 | View source ↗Organizer evaluated | |
AnimateLCMText-to-videoNot specified by source | 79.42 | 82.36 | 67.65 | View source ↗Organizer evaluated | |
LTX-2 (Diffusers) (w/o prompt-optimized)Text-to-videoNot specified by source | 79.35 | 84.10 | 60.34 | View source ↗Organizer evaluated | |
Show-1Text-to-videoNot specified by source | 78.93 | 80.42 | 72.98 | View source ↗Organizer evaluated | |
OpenSoraPlan V1.1Text-to-videoNot specified by source | 78.00 | 80.91 | 66.38 | View source ↗Organizer evaluated | |
MAGI-T2V-4.5B-distillText-to-videoNot specified by source | 77.92 | 80.98 | 65.68 | View source ↗Organizer evaluated | |
AnimateDiff-V1Text-to-videoNot specified by source | 77.46 | 80.24 | 66.32 | View source ↗Organizer evaluated | |
HiGenText-to-videoNot specified by source | 77.34 | 80.35 | 65.27 | View source ↗Organizer evaluated | |
Latte-1Text-to-videoNot specified by source | 77.29 | 79.72 | 67.58 | View source ↗Organizer evaluated | |
OpenSoraPlan V1.3Text-to-videoNot specified by source | 77.23 | 80.14 | 65.62 | View source ↗Organizer evaluated | |
LaVie-InterpolationText-to-videoNot specified by source | 77.11 | 79.06 | 69.28 | View source ↗Organizer evaluated | |
LaVieText-to-videoNot specified by source | 77.08 | 78.78 | 70.31 | View source ↗Organizer evaluated | |
InstructVideo (ModelScope)Text-to-videoNot specified by source | 76.61 | 81.56 | 56.81 | View source ↗Organizer evaluated | |
OpenSoraPlan V1.2Text-to-videoNot specified by source | 75.98 | 81.51 | 53.88 | View source ↗Organizer evaluated | |
Open-SoraText-to-videoNot specified by source | 75.91 | 78.82 | 64.28 | View source ↗Organizer evaluated | |
ModelScopeText-to-videoNot specified by source | 75.75 | 78.05 | 66.54 | View source ↗Organizer evaluated | |
OpenSora V1.1Text-to-videoNot specified by source | 75.66 | 77.74 | 67.36 | View source ↗Organizer evaluated | |
TF-T2VText-to-videoNot specified by source | 75.38 | 80.05 | 56.69 | View source ↗Organizer evaluated | |
VideoCrafter-0.9Text-to-videoNot specified by source | 73.02 | 74.91 | 65.46 | View source ↗Organizer evaluated | |
MiraText-to-videoNot specified by source | 71.87 | 78.78 | 44.21 | View source ↗Organizer evaluated | |
CogVideoText-to-videoNot specified by source | 67.01 | 72.06 | 46.83 | View source ↗Organizer evaluated |
Official VBench 1.0 T2V leaderboard. Percentages are copied as published; Rather does not recompute totals. Generation, scoring teams and certification vary by submission. Other VBench tracks are not included. A reported score is not an independent verification by Rather.