Skip to contentT/TTokens or Towers

Compare

LeaderboardEvery tracked model, ranked and priced side by sideBenchmarksWhat each test measures and who leads itPricesAPI, media, and hardware rates with a cost calculator

Plan

Stack plannerSix questions to a priced local and hosted stackShortlistOur picks for subscriptions, APIs, and hardwareEnterpriseSeat plans against self-hosting for a whole team

Build

HardwareGPUs and workstations, and which models they fitHostsWhere to rent open-weight inference, and for how muchHarnessesCoding agents and the models they drive

Lab

FindingsResults from our own evaluationsScanAudit a repo’s AI usage in the browserMethodWhere the numbers come from and how we check them
Data checked September 25, 2026
Data checked September 25, 2026
Plan a stack
T/TTokens or Towers

An independent guide to AI models, what they cost, and the hardware to run them. No account, no API key, no sponsors.

Compare

  • Leaderboard
  • Benchmarks
  • Prices

Plan

  • Stack planner
  • Shortlist
  • Enterprise

Build

  • Hardware
  • Hosts
  • Harnesses

Lab

  • Findings
  • Scan
  • Method
Data checked September 25, 2026 · Every number links to its sourceRSS · Source on GitHub
Leaderboard/Kuaishou
Kuaishou

Kuaishou · Kling 3.0

Kling 3.0 Omni

Closed weightsGenerally availableproprietary

Kling 3.0 variant for reference- and video-input generation and editing.

Best arena Elo
1280
Price
$0.112per second of 1080p video, no video input, no audio (with audio $0.14/s; with video input $0.168/s; 720p from $0.084/s; 4K $0.42/s)
Output speed
—
Output
video, audio

Image and video generation

  • Artificial Analysis Video Arena: text to video with audio#14 of 20
    1082independentwith audio; AA entry "Kling 3.0 Omni 720p (Standard)"; rank 18; 95% CI ±7; 7265 appearancesArtificial Analysis Video Arena: Text to Video leaderboard ↗
    1075independentwith audio; AA entry "Kling 3.0 Omni 1080p (Pro)"; rank 22; 95% CI ±7; 7396 appearancesArtificial Analysis Video Arena: Text to Video leaderboard ↗

    Leader: Gemini Omni 1.1 Flash at 1233

  • Artificial Analysis Video Arena: text to video, silent#9 of 24
    1230independentwithout audio; AA entry "Kling 3.0 Omni 1080p (Pro)"; rank 11; 95% CI ±8; 4566 appearancesArtificial Analysis Video Arena: Text to Video leaderboard ↗
    1215independentwithout audio; AA entry "Kling 3.0 Omni 720p (Standard)"; rank 18; 95% CI ±8; 4448 appearancesArtificial Analysis Video Arena: Text to Video leaderboard ↗

    Leader: Wan 3.0 at 1335

  • Artificial Analysis Video Arena: image to video with audio#17 of 19
    1045independentwith audio; AA entry "Kling 3.0 Omni 1080p (Pro)"; rank 21; 95% CI ±7; 6107 appearancesArtificial Analysis Video Arena: Image to Video leaderboard ↗
    1035independentwith audio; AA entry "Kling 3.0 Omni 720p (Standard)"; rank 23; 95% CI ±7; 6128 appearancesArtificial Analysis Video Arena: Image to Video leaderboard ↗

    Leader: MiniMax H3 Max at 1194

  • Artificial Analysis Video Arena: image to video, silent#11 of 23
    1280independentwithout audio; AA entry "Kling 3.0 Omni 1080p (Pro)"; rank 16; 95% CI ±10; 3945 appearancesArtificial Analysis Video Arena: Image to Video leaderboard ↗
    1271independentwithout audio; AA entry "Kling 3.0 Omni 720p (Standard)"; rank 21; 95% CI ±10; 4035 appearancesArtificial Analysis Video Arena: Image to Video leaderboard ↗

    Leader: Gemini Omni 1.1 Flash at 1369

Specs

Released
February 4, 2026
Parameters
Undisclosed
Size class
Undisclosed
Input
text, image, video
Output
video, audio
  • Price: Kling API pricing ↗

Compare with

  • KuaishouKling 3.0
  • KuaishouKling 3.0 Turbo
  • GoogleGemini Omni 1.1 Flash
  • GoogleVeo 3.1