Alibaba: Wan 2.6

Alibaba's most advanced video generation model, supporting over 10 visual creation capabilities in a unified system. Wan 2.6 generates 1080p video at 24fps from text, images, reference videos, or aud…

alibaba/wan-2.6-20260327

Alibaba's most advanced video generation model, supporting over 10 visual creation capabilities in a unified system. Wan 2.6 generates 1080p video at 24fps from text, images, reference videos, or audio, with native audio-visual synchronization and precise lip-sync. Key features include reference-to-video (insert a character's appearance and voice into new scenes), multi-shot storytelling from simple prompts, synchronized sound effects and music, and support for 16:9, 9:16, and 1:1 aspect ratios with clips up to 15 seconds.

Specifications & capabilities

Input
text, image
Output
video
Context window · tokens
0
Capabilities
multimodal, videoOutput, visionInput
Description source ↗

Evaluations

1–11 / 11

LMArena

1,147.905

source id
lmarena
leaderboard name
LMArena Text To Image Agentic
dimension
multimodal
metric
Arena rating
rank
18
sample size
5109
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1136.4402985420254
confidence upper
1159.3696388777773
Original result ↗

LMArena

1,323.505

source id
lmarena
leaderboard name
LMArena Text To Video Overall
dimension
multimodal
metric
Arena rating
rank
23
sample size
75753
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1316.4499813519362
confidence upper
1330.5599125964413
Original result ↗

LMArena

1,309.132

source id
lmarena
leaderboard name
LMArena Image To Video Overall
dimension
multimodal
metric
Arena rating
rank
25
sample size
141910
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1302.5402670700491
confidence upper
1315.7229024398023
Original result ↗

LMArena

1,149.954

source id
lmarena
leaderboard name
LMArena Text To Image 3d Modeling
dimension
multimodal
metric
Arena rating
rank
35
sample size
23270
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1144.1033191133333
confidence upper
1155.804669564032
Original result ↗

LMArena

1,158.546

source id
lmarena
leaderboard name
LMArena Text To Image Art
dimension
multimodal
metric
Arena rating
rank
37
sample size
31788
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1153.2431300868657
confidence upper
1163.8491678682244
Original result ↗

LMArena

1,148.526

source id
lmarena
leaderboard name
LMArena Text To Image Text Rendering
dimension
multimodal
metric
Arena rating
rank
38
sample size
86499
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1144.411875327154
confidence upper
1152.6396924702033
Original result ↗

LMArena

1,147.2

source id
lmarena
leaderboard name
LMArena Text To Image Cartoon
dimension
multimodal
metric
Arena rating
rank
38
sample size
98110
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1143.129044505401
confidence upper
1151.2701353814903
Original result ↗

LMArena

1,149.408

source id
lmarena
leaderboard name
LMArena Text To Image Commercial Design
dimension
multimodal
metric
Arena rating
rank
39
sample size
90132
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1145.42103208379
confidence upper
1153.3951173540909
Original result ↗

LMArena

1,138.483

source id
lmarena
leaderboard name
LMArena Text To Image Overall
dimension
multimodal
metric
Arena rating
rank
42
sample size
248684
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1135.7282316455628
confidence upper
1141.2386851674858
Original result ↗

LMArena

1,130.934

source id
lmarena
leaderboard name
LMArena Text To Image Photorealistic
dimension
multimodal
metric
Arena rating
rank
47
sample size
99058
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1126.9350777591153
confidence upper
1134.9323783230398
Original result ↗

LMArena

1,126.267

source id
lmarena
leaderboard name
LMArena Text To Image Portraits
dimension
multimodal
metric
Arena rating
rank
52
sample size
53737
evaluated at
2026-11-09T00:00:00.000Z
source model id
Wan 2.6
confidence lower
1121.4248836348186
confidence upper
1131.108230067599
Original result ↗

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

26 / 100

source id
stanfordFMTI
canonical model id
alibaba/wan-2.6-20260327
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Alibaba
assessment type
organization-level disclosure
metric
disclosure_score
result label
26 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Original sources

1–4 / 4

OpenRouter · Model page ↗

GitHub · Catalog ↗

LMArena · Catalog ↗

OpenRouter · Catalog ↗

Source links

1–3 / 3

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace