whatmodel.sh / video / HappyHorse 1.0

HappyHorse 1.0

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

HappyHorse 1.0 is a closed-weights video model from Alibaba-ATH, released April 2026. Licence: proprietary.

72.7±1.6#13 of 93 video modelsfrom 5 benchmark results across 3 sources

$ how it compares

The video models ranked either side of HappyHorse 1.0, out of 139 with a score.

#modelscorewhereRAMreleased
13HiDream-O1-Video 1.0 HiDream75±3comparison only
14Wan 2.2 I2V Flash Alibaba75±4api $0.036/sec2025-08
15HappyHorse 1.0 Alibaba-ATH73±2api $0.14/sec2026-04
16Wan 2.2 I2V Plus Alibaba71±5api $0.10/sec2025-07
17Grok Imagine Video xAI69±2api $0.050/sec2026-01

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▃▄ #9 of 68 * · 43% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
LMArena video1427.2 ✎▂▂▃▆█▆·▆▅▃▂▇ beats 33/41avg 1147▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%typical
image to video▁▂·▂▅█▅▄▅▆▃▄ #12 of 50 * · 45% of its score · 2 tests

Beats HappyHorse 1.1 here, though they rank higher overall. Trails Kling 3.0, Grok Imagine Video here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image-to-video1441.7 ✎▁▁▁▁▄▇▃▆▃▂▄█ beats 31/40avg 1189▇▇▇▇▇▇▇▇▇▇▇ 29%typical
Rapidata physics realism (I2V, with reference)1085.0 ✎▂··▂▂▆█▆▂▂▆▄ beats 9/19avg 741▇▇▇▇▇▇▇ 16%sharp
video editing▄··█··▄··█▄█ #6 of 9 * · 8.8% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
Arena video edit1306.7 ✎█··█··▄··█▄█ beats 4/9avg 1117▇▇▇▇ 8.8%typical
other tests1 not in a task · 1.8% of its score
testresultvs the others in its rundifficultycountswhy
MechVerse mechanical-motion I2V (WorldModelBench-judge sum)75.6% ✎▂···▂······█ beats 3/5medium · avg 65%▇ 1.8%blunt

$ where to run it

Through an API

api · Replicate · $0.14/sec · replicate.com ↗ · price sourceUSD per output video second. Text-to-video, 720p output, no starting image; 3–15 second clips. 1080p costs $0.28/output-second. Replicate output/character billing; hardware-time rates are not added to this tariff. Taxes and separate services excluded. Bertrande, https://bertrande.com/en/ai/replicate/alibaba--happyhorse-1.0; observed 2026-09-20T01:44:15Z. CC BY 4.0; units normalized and model identifier mapped.

$ how the score was worked out · LMArena leaderboard dataset 81%, Rapidata/world-model-physics… 16%, MechVerse: Evaluating Physica… 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 dataset3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%CC BY 4.0
Rapidata/world-model-physics published dataset-card rankings1▇▇▇▇▇ 16%CC-BY-4.0
MechVerse: Evaluating Physical Motion Consistency in Video Generation Models (arXiv:2605.14843v1)1▇ 2%CC-BY-4.0
prior · pull toward the middle▇ 1%
weighted average= 72.7

$ 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