whatmodel.sh / video / Veo 2

Veo 2

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Veo 2 is a closed-weights video model from Google, released April 2025.

Model information sources

Release date ↗

49.5±1.8comparison only: no current run option verifiedfrom 3 benchmark results across 2 sources

$ how it compares

The video models ranked either side of Veo 2, out of 139 with a score, then more from Google.

#modelscorewhereRAMreleased
67Wan 2.2 A14B Alibaba50±2api $0.080/sec +local~31GB2025-07
68Runway Gen-4 Runway50±4comparison only2025-03
69Veo 2 Google50±2comparison only2025-04
70LTX-2 Lightricks49±2local~120GB2025-10
71Open-Sora Plan v1.3 (T2V) Peking University (PKU-YuanGroup)49±7local~24GB2024-10
more from Google
1Gemini Omni 1.1 Flash Google81±2api $0.10/sec2026-08
3Gemini Omni Flash Google80±2api $0.10/sec2026-05
19Veo 3.1 Google69±1api $0.40/sec2025-10

see all video models · find the ones that fit your machine

$ what it's good at

text to video▇▅▄▆█▆▇▂▃▃▂▄ #37 of 94 * · 55% of its score · 1 test

Beats Kling 2.1 Master, PixVerse 5.5, LongCat-Video here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
LMArena video1164.4 ✎▂▂▃▆█▆·▆▅▁▂▇ beats 9/41avg 1147▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 55%typical
image to video▁▁▂▃██▄▃▃▄▂▂ #65 of 74 * · 43% of its score · 2 tests

Trails Wan 2.1 I2V Turbo, HunyuanVideo-I2V, Hailuo 01 (MiniMax video-01 / I2V-01) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image-to-video1165.8 ✎▁▁▁▁▄▇▃▆▃▂▄█ beats 4/40avg 1189▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 36%typical
MagicArena image-to-video Elo (Seaweed-7B report)992.0 ✎▄·····▄█··▄▄ beats 1/5avg 1043▇▇▇ 7.0%typical

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 92%, Seaweed-7B: Cost-Effective Tr… 7%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 92%CC BY 4.0
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model1▇▇ 7%CC-BY-4.0
prior · pull toward the middle▇ 1%
weighted average= 49.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json