whatmodel.sh / video / Pika 2.2

Pika 2.2

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

Pika 2.2 is a closed-weights video model from Pika, released February 2025. Licence: proprietary.

36.0±1.8#78 of 93 video modelsfrom 4 benchmark results across 3 sources

$ how it compares

The video models ranked either side of Pika 2.2, out of 139 with a score, then more from Pika.

#modelscorewhereRAMreleased
113CogVideoX1.5-5B Zhipu AI (THUDM)36±2local~38GB2024-11
114CogVideoX-2B Zhipu AI (THUDM)36±2local~5.3GB2024-08
115Pika 2.2 Pika36±2api $0.040/sec2025-02
116Allegro Rhymes AI35±2local~9.3GB2024-10
117Kling 1.0 Kuaishou (Kling AI)35±7comparison only2024-06
more from Pika
120Pika 1.0 Pika32±3comparison only2023-11
132PikaLab (September 2023) Pika27±2comparison only2023-09

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #50 of 68 · 63% of its score · 3 tests

Beats T2V-Turbo (VC2), CogVideoX1.5-5B, CogVideoX-2B here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
LMArena video1009.0 ✎▃▂▃▆█▆·▆▅▁▂▇ beats 1/41avg 1147▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 54%typical
T2VPhysBench (human physical consistency)32.0% ✎█··█·█·····█ beats 1/3medium · avg 46%▇▇ 5.9%at its level
HumanScore (T2V)81.6% ✎▂··▃··█▄▂··▆ beats 1/11easy · avg 84%▇ 2.3%blunt
image to video▃▂·▂▅█▅▄▅▆▃▄ #50 of 50 * · 36% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
Arena image-to-video997.1 ✎▃▁▁▁▄▇▃▆▃▂▄█ beats 0/40avg 1189▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 36%typical

$ where to run it

Through an API

api · fal.ai · $0.040/sec · fal.ai ↗ · price sourceUSD per second, derived from fal's price of $0.20 for a 5-second 720p video (÷ 5). Product: fal Pika 2.2 text-to-video endpoint. API model: fal-ai/pika/v2.2/text-to-video. Settings: resolution=720p, duration=5 s (endpoint default). 5-s 1080p costs $0.45; other durations are not separately priced on the page. Currency: USD. fal.ai model page, observed 2026-09-25.

$ how the score was worked out · LMArena leaderboard dataset 90%, T2VPhysBench: A First-Princip… 6%, HumanScore: Benchmarking Huma… 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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 90%CC BY 4.0
T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation1▇▇ 6%CC-BY-4.0
HumanScore: Benchmarking Human Motions in Generated Videos1▇ 2%CC-BY-4.0
prior · pull toward the middle▇ 1%
weighted average= 36.0

$ 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