whatmodel.sh / video / Kling 2.6 Pro

Kling 2.6 Pro

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

Kling 2.6 Pro is a closed-weights video model from Kuaishou (Kling AI), released December 2025. Licence: proprietary.

59.3±1.6#27 of 93 video modelsfrom 4 benchmark results across 3 sources

$ how it compares

The video models ranked either side of Kling 2.6 Pro, out of 139 with a score, then more from Kuaishou (Kling AI).

#modelscorewhereRAMreleased
32Seedance 1.0 Pro Fast ByteDance62±11api $0.049/sec
33Wan 2.5 Preview Alibaba61±2api $0.10/sec2025-09
34Kling 2.6 Pro Kuaishou (Kling AI)59±2api $0.070/sec2025-12
35PixVerse V5.6 PixVerse59±2api $0.045/sec2026-02
36Runway Gen-4.5 Runway58±2api $0.12/sec2025-12
more from Kuaishou (Kling AI)
22Kling 3.0 Kuaishou (Kling AI)68±4api $0.084/sec2026-02
31Kling O3 Pro Kuaishou (Kling AI)64±4api $0.11/sec
44Kling O1 Pro Kuaishou (Kling AI)56±2api $0.11/sec

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #21 of 68 * · 52% of its score · 2 tests

Trails Kling 2.5 Turbo Pro, Seedance 1.5 Pro, Runway Gen-4.5 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena video1216.2 ✎▂▂▃▆█▆·▆▅▁▂▇ beats 18/41avg 1147▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 45%typical
WorldJen human preference (Bradley-Terry)1572.0 ✎█···██·█··██ beats 4/5avg 1470▇▇▇ 6.5%typical
image to video▁▂·▂▅█▅▄▅▆▃▄ #20 of 50 * · 47% of its score · 2 tests

Beats HappyHorse 1.1, Vidu Q3 Pro, Wan 2.5 Preview here, though they rank higher overall. Trails Runway Gen-4.5 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena image-to-video1294.0 ✎▁▁▁▁▄▇▃▆▃▂▄█ beats 18/40avg 1189▇▇▇▇▇▇▇▇▇▇▇▇ 30%typical
Rapidata physics realism (I2V, with reference)1034.0 ✎▂··▂▂▆█▆▂▂▆▄ beats 6/19avg 741▇▇▇▇▇▇▇ 17%sharp

$ where to run it

Through an API

api · fal.ai · $0.070/sec · fal.ai ↗ · price sourceUSD per second of generated video on fal.ai, audio off. Product: fal Kling 2.6 Pro text-to-video endpoint. API model: fal-ai/kling-video/v2.6/pro/text-to-video. Settings: generate_audio=false (the endpoint default is true, which costs $0.14/s). Price basis: per-second rate printed by fal. Not the Kling direct tariff. Currency: USD. fal.ai model page, observed 2026-09-25.

$ how the score was worked out · LMArena leaderboard dataset 75%, Rapidata/world-model-physics… 17%, WorldJen: An End-to-End Multi… 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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 75%CC BY 4.0
Rapidata/world-model-physics published dataset-card rankings1▇▇▇▇▇ 17%CC-BY-4.0
WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models1▇▇ 7%CC-BY-4.0
prior · pull toward the middle▇ 1%
weighted average= 59.3

$ 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