whatmodel.sh / video / Hailuo 02

Hailuo 02

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

Hailuo 02 is a closed-weights video model from MiniMax, released June 2025.

Model information sources

Release date ↗

53.5±1.8#42 of 93 video modelsfrom 4 benchmark results across 3 sources

$ how it compares

The video models ranked either side of Hailuo 02, out of 139 with a score, then more from MiniMax.

#modelscorewhereRAMreleased
50Vidu Q3 Shengshu54±12comparison only2026-01
51Kling 2.1 Standard Kuaishou (Kling AI)54±3api $0.050/sec2025-05
52Hailuo 02 MiniMax54±2api $0.047/sec2025-06
53LTX-2.5 Lightricks53±6api $0.12/sec +local~14GB2026-08
54Vidu Q2 Pro ShengShu (Vidu)53±3comparison only2025-09
more from MiniMax
6MiniMax H3 MiniMax78±1api $0.13/sec +local~40GB2026-07
10MiniMax H3 Max MiniMax76±4api $0.080/sec2026-09
48Hailuo 2.3 MiniMax55±2api $0.047/sec2025-10

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #27 of 68 * · 59% of its score · 2 tests
testresultvs the others in its rundifficultycountswhy
LMArena video1181.1 ✎▂▂▃▆█▆·▆▅▁▂▇ beats 12/41avg 1147▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 57%typical
HumanScore (T2V)85.8% ✎▂··▂··█▄▂··▆ beats 4/11easy · avg 84%▇ 1.8%blunt
image to video▁▂·▂▅█▅▄▅▆▃▄ #35 of 50 * · 39% of its score · 2 tests

Beats Seedance 1.5 Pro, Kling 2.1 Standard here, though they rank higher overall. Trails Cosmos3-Nano here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image-to-video1223.7 ✎▁▁▁▁▄▇▃▆▃▂▄█ beats 9/40avg 1189▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 38%typical
V-ReasonBench (average pass@5)37.5% ✎█·····▄···▄▄ beats 3/4hard · avg 17%▇ 1.7%noisy

$ where to run it

Through an API

api · $0.047/sec · platform.minimax.io ↗ · price sourceUSD per second of output video, 768P, derived from MiniMax's pay-as-you-go price of $0.28 per 768P 6-second video (÷ 6). Product: MiniMax video generation (listed under Legacy Models). API model: MiniMax-Hailuo-02. Settings: resolution=768P, duration=6 s. 10-s 768P $0.56 ($0.056/s); 6-s 1080P $0.49; 6-s 512P $0.10. Currency: USD. MiniMax pay-as-you-go pricing page, observed 2026-09-25.

$ how the score was worked out · LMArena leaderboard dataset 95%, HumanScore: Benchmarking Huma… 2%, V-ReasonBench: Toward Unified… 2%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%CC BY 4.0
HumanScore: Benchmarking Human Motions in Generated Videos1▇ 2%CC-BY-4.0
V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models1▇ 2%CC-BY-4.0
prior · pull toward the middle▇ 1%
weighted average= 53.5

$ 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