whatmodel.sh / video / Ray 2

Ray 2

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

Ray 2 is a closed-weights video model from Luma AI, released January 2025.

Model information sources

Release date ↗

42.7±1.7comparison only: no current run option verifiedfrom 4 benchmark results across 3 sources

$ how it compares

The video models ranked either side of Ray 2, out of 139 with a score, then more from Luma AI.

#modelscorewhereRAMreleased
92Step-Video-TI2V StepFun44±7comparison only2025-03
93Wan 2.1 I2V Turbo Alibaba43±7api price unknown2025-02
94Ray 2 Luma AI43±2comparison only2025-01
95Open-Sora 2.0 HPC-AI Tech42±5local~55GB2025-03
96Pyramid Flow (SD3) Peking University / Kuaishou42±3local~8GB2024-10
more from Luma AI
49Ray 3 Luma AI55±2comparison only2025-09
66Luma Dream Machine 1.6 Luma AI50±7comparison only2024-09
97Luma Dream Machine 1.0 Luma AI42±7comparison only2024-06

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

$ what it's good at

text to video▇▅▄▆█▆▇▂▃▃▂▄ #55 of 94 * · 61% of its score · 2 tests
testresultvs the others in its rundifficultycountswhy
LMArena video1065.4 ✎▂▃▃▆█▆·▆▅▁▂▇ beats 2/41avg 1147▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%typical
VideoPhy-2 (human, joint SA & PC)20.3% ✎▄···▄·▄·█··▄ beats 2/5hard · avg 33%▇▇▇▇▇ 14%typical
image to video▁▁▃▂██▄▃▃▄▂▂ #67 of 74 * · 38% of its score · 2 tests
testresultvs the others in its rundifficultycountswhy
Arena image-to-video1108.5 ✎▁▁▃▁▄▇▃▆▃▂▄█ beats 2/40avg 1189▇▇▇▇▇▇▇▇▇▇▇▇▇ 31%typical
MagicArena image-to-video Elo (Seaweed-7B report)1003.0 ✎▄·····▄█··▄▄ beats 3/5avg 1043▇▇ 6.1%typical

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 79%, VideoPhy / VideoPhy-2 officia… 14%, Seaweed-7B: Cost-Effective Tr… 6%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 79%CC BY 4.0
VideoPhy / VideoPhy-2 official repository leaderboards1▇▇▇▇ 14%MIT
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model1▇▇ 6%CC-BY-4.0
prior · pull toward the middle▇ 1%
weighted average= 42.7

$ 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