← All model leaderboards · Updated 2026-04-06

text to video

Text to Video Model Leaderboard

Compare the top AI video generation models across Artificial Analysis, Design Arena, and Arena AI - unified rankings, source-by-source scores, speed, and API pricing in one table.

Top consensus: Dreamina Seedance 2.0 720p

Try AI video generation

Models ranked

41

in this table

Leading model

Dreamina Seedance 2.0 720p

100.0 consensus

Median consensus

54.8

typical model in this list

Gap to 2nd

3.0 pts

consensus points, 1st vs 2nd

Showing 41 of 41 · Snapshot 2026-04-06
SourcesArtificial AnalysisDesign ArenaArena AI
🥇

Dreamina Seedance 2.0 720p

ByteDance Seed

100.0

AA

#1

1274

DA

—

—

Ar

—

—

Speed 35s—
🥈

SkyReels V4

Skywork AI

97.0

AA

#2

1245

DA

—

—

Ar

—

—

Speed —$7.20/min
🥉

PixVerse V6

PixVerse

90.9

AA

#4

1240

DA

—

—

Ar

—

—

Speed —$5.40/min
4

grok-imagine-video

xAI

90.3

AA

#6

1229

DA

#1

1328

Ar

#6

1358

Speed 23.1s$4.20/min
5

Kling 3.0 Omni 1080p (Pro)

KlingAI

87.9

AA

#5

1231

DA

—

—

Ar

—

—

Speed —$13.44/min
6

Kling 3.0 1080p (Pro)

KlingAI

87.7

AA

#3

1241

DA

#6

1273

Ar

—

—

Speed 218s$13.44/min
7

Wan 2.7

Alibaba

85.2

AA

—

—

DA

#5

1276

Ar

—

—

Speed 214s—
8

Veo 3.1

Google

84.2

AA

#13

1215

DA

#4

1276

Ar

#1

1381

Speed 48.9s$12.00/min
9

Veo 3.1 Fast

Google

83.5

AA

#14

1214

DA

#3

1279

Ar

#2

1378

Speed 43.8s$6.00/min
10

Vidu Q3 Pro

Vidu

75.8

AA

#9

1224

DA

—

—

Ar

—

—

Speed 138.7s$9.60/min
11

Veo 3

Google

73.3

AA

#10

1221

DA

#7

1259

Ar

#12

1257

Speed 42.4s$12.00/min
12

PixVerse V5.6

PixVerse

71.5

AA

#7

1228

DA

—

—

Ar

#15

1228

Speed —$9.00/min
13

Kling 3.0 Omni 720p (Standard)

KlingAI

69.7

AA

#11

1219

DA

—

—

Ar

—

—

Speed 70.4s$10.08/min
14

Sora 2 Pro

OpenAI

69.2

AA

#19

1196

DA

#9

1248

Ar

#4

1367

Speed 136s$30.00/min
15

Veo 3 Fast Preview

Google

68.0

AA

#23

1177

DA

#2

1290

Ar

#7

1351

Speed 39.8s$9.00/min
16

Kling 3.0 720p (Standard)

KlingAI

66.7

AA

#12

1218

DA

—

—

Ar

—

—

Speed 64.3s$10.08/min
17

Runway Gen-4.5

Runway

65.8

AA

#8

1227

DA

—

—

Ar

#18

1214

Speed ——
18

Wan 2.6

Alibaba

58.5

AA

#20

1189

DA

—

—

Ar

#8

1347

Speed —$9.00/min
19

Sora 2 (December)

OpenAI

57.7

AA

#24

1176

DA

#8

1248

Ar

#9

1342

Speed 87s$6.00/min
20

Kling 2.5 Turbo 1080p

KlingAI

55.9

AA

#15

1213

DA

#14

1183

Ar

#16

1221

Speed 89s$4.20/min
21

Kling O1 Pro (January)

KlingAI

54.8

AA

#16

1205

DA

#11

1204

Ar

#19

1208

Speed 95s$10.08/min
22

Kling 2.6 Pro (January)

KlingAI

54.4

AA

#18

1203

DA

#12

1201

Ar

#17

1219

Speed 115s$4.20/min
23

Ray 3

Luma Labs

52.4

AA

#17

1205

DA

#13

1197

Ar

#20

1204

Speed 64s$13.20/min
24

Seedance 1.5 pro

ByteDance Seed

50.5

AA

#25

1175

DA

#10

1208

Ar

#13

1255

Speed 83s$5.93/min
25

MiniMax Hailuo-2.3 (Standard)

MiniMax

44.4

AA

—

—

DA

#16

1175

Ar

—

—

Speed 103s—
26

Wan 2.5 Preview

Alibaba

42.2

AA

#26

1166

DA

—

—

Ar

#11

1268

Speed 102s$9.00/min
27

Glam.ai 1.0

Glam.ai

40.7

AA

—

—

DA

#17

1155

Ar

—

—

Speed 156s—
28

Hailuo 2.3

MiniMax

40.0

AA

#21

1184

DA

#15

1182

Ar

#22

1196

Speed 186s$2.80/min
29

P-Video (1080p)

Pruna AI

37.0

AA

—

—

DA

#18

1146

Ar

—

—

Speed 30.7s—
30

Hailuo 02 Standard

MiniMax

31.7

AA

#22

1179

DA

—

—

Ar

#24

1181

Speed —$2.80/min
31

P-Video (720p)

Pruna AI

29.6

AA

—

—

DA

#20

1123

Ar

—

—

Speed 13.1s—
32

Kandinsky 5.0 Pro

AI Forever

28.2

AA

—

—

DA

#21

1100

Ar

#26

1179

Speed 268s—
33

Hailuo 02 Pro

MiniMax

25.3

AA

#27

1164

DA

—

—

Ar

#21

1200

Speed —$4.90/min
34

Seedance 1.0

ByteDance Seed

24.1

AA

#28

1141

DA

#19

1125

Ar

#23

1192

Speed 56s$7.32/min
35

WAN 2.1 T2V 14B

Alibaba

22.2

AA

—

—

DA

#22

1075

Ar

—

—

Speed 60s—
36

Kandinsky 5.0

AI Forever

18.5

AA

—

—

DA

#23

1070

Ar

—

—

Speed 200s—
37

LTX-2 19B

Lightricks

15.7

AA

—

—

DA

#24

1052

Ar

#31

1122

Speed 58.9s—
38

WAN 2.2 T2V 14B

Alibaba

15.3

AA

—

—

DA

#25

1052

Ar

#30

1130

Speed 48.7s—
39

Hunyuan Video

Tencent

13.9

AA

—

—

DA

#28

972

Ar

#27

1175

Speed 602s—
40

Ray 2

Luma Labs

6.5

AA

—

—

DA

#26

1044

Ar

#35

1066

Speed 133s—
41

Ray 2 Flash

Luma Labs

3.7

AA

—

—

DA

#27

1030

Ar

—

—

Speed 36.6s—

Methodology

Each source uses preference data to estimate skill scores. We map ranks to percentiles and average where a model appears on multiple lists. The bar in the Consensus column is green; purple, rose, amber match Artificial Analysis, Design Arena, Arena AI columns. Speed is approximate time to the first image.

FAQ

Answers below use the same snapshot as the table above (as of 2026-04-06, 41 models). Figures are from our export, not live pages at Artificial Analysis, Design Arena, or Arena AI—those sites may have moved on since we built this snapshot. The Consensus column is our average of percentile ranks across benchmarks where each model appears.

We use each model's released field from the export. Among rows with a parseable date, the newest in this snapshot include: Dreamina Seedance 2.0 720p (2026-03-01); SkyReels V4 (2026-03-01); PixVerse V6 (2026-03-01).

By default we sort by Consensus, so Dreamina Seedance 2.0 720p leads this snapshot at 100.0 (average percentile across benchmarks where the model appears). By Elo in the Artificial Analysis column alone, Dreamina Seedance 2.0 720p is highest at 1274. “Best” still depends on price, latency, and which benchmarks you care about—use the sortable table.

The Elo values below are the Artificial Analysis numbers in this export (2026-04-06), not necessarily what you see on Artificial Analysis today:
  1. Dreamina Seedance 2.0 720p — Elo 1274
  2. SkyReels V4 — Elo 1245
  3. Kling 3.0 1080p (Pro) — Elo 1241
  4. PixVerse V6 — Elo 1240
  5. Kling 3.0 Omni 1080p (Pro) — Elo 1231

Text-to-video models generate video clips from a text prompt alone. Image-to-video models take both a reference image and a text prompt, then animate the image into a video clip. Our table is built for text-to-video leaderboards from the sources named in the header.

Each upstream source runs preference tests and publishes ranks or scores. We map those to percentiles within each benchmark, then average across benchmarks where a model appears—that is the Consensus column (see Methodology above the FAQ). Per-source columns show the ranks and scores stored in our snapshot for Artificial Analysis, Design Arena, and Arena AI. To change upstream leaderboards, participate on those sites; our table updates when we refresh the export.

We flag open-weights rows from the export name suffix “Open Weights”. By Artificial Analysis Elo in this snapshot, the highest are:
No open-weights rows with Elo in this export.
Treat naming as a signal only—confirm license terms with each provider before production use.

Elo in our table is the value from the snapshot for the Artificial Analysis column (and similar skill estimates elsewhere). Margin of error / intervals (e.g. in CI columns) come from that same export. For how Artificial Analysis computes Elo from votes, see their methodology; our numbers stay fixed until the next snapshot refresh.