Benchmark
Image to video leaderboard
Board: Overall · Hands · Faces · Liquids · On-screen text · Multi-shot · Lip-sync · Camera · Animals · Style · Image to video · Animation
Look: Realism · Animation and 3D
Round: all · v1-vivix-2026-10 · v1-2026-10 · v1-2026-09 · anim1-2026-10
Clip shown: every model here on the same prompt, “i2v-portrait-animate”, so the preview is a fair comparison, not a cherry-picked best clip.
| # | Model | Clip | Overall | 95% CI | Fidelity | Visual | Physics | Consistency | Audio | Attempts | Gen (s) | $/run | Runs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |  OpenAI Sora 2
discontinued OpenAI |
5.00 | ±0 | 5.00 | 5.00 | — | — | — | 1.00 | 217 | — | 4 | |
| 2 |  Kling 3.0
Kuaishou |
5.00 | ±0 | 5.00 | 5.00 | — | — | — | 1.00 | 190 | — | 4 | |
| 3 |  Grok Video
xAI |
5.00 | ±0 | 5.00 | 5.00 | — | — | — | 1.00 | 85 | — | 4 | |
| 4 |  Seedance 2.0
ByteDance |
5.00 | ±0 | 5.00 | 5.00 | — | — | — | — | 292 | — | 4 | |
| 5 | Seedance 2.5
ByteDance |
5.00 | ±0 | 5.00 | 5.00 | — | — | — | — | 233 | — | 4 | |
| 6 |  Google Veo 3.1
|
5.00 | ±0 | 5.00 | 5.00 | — | — | — | — | 75 | — | 4 | |
| 7 |  MiniMax Hailuo 02
MiniMax |
5.00 | ±0 | 5.00 | 5.00 | — | — | — | — | 300 | — | 4 | |
| 8 | MiniMax H3
MiniMax |
5.00 | ±0 | 5.00 | 5.00 | — | — | — | — | 448 | — | 4 | |
| 9 | Kling 3.0 Turbo
Kuaishou |
5.00 | ±0 | 5.00 | 5.00 | 5.00 | 5.00 | 5.00 | — | — | — | 4 | |
| 10 | Google Gemini Omni
|
4.96 | ±0 | 5.00 | 5.00 | 5.00 | 5.00 | 4.80 | — | — | — | 4 | |
| 11 |  PixVerse v5.5
PixVerse |
4.93 | ±0.21 | 4.88 | 4.95 | 4.95 | 4.95 | — | — | — | — | 4 | |
| 12 |  Runway Gen-4.5
Runway |
4.59 | ±0.76 | 4.70 | 4.50 | 4.58 | 4.58 | — | — | — | — | 4 |
Attempts is the average number of generations needed before one was usable, the number that actually decides what a model costs you. 95% CI is computed from that model's own runs on this board, not assumed. On a category board with only 4 runs per model, a wide CI is the honest reflection of a small sample, not a bug. Two models whose CIs overlap are not meaningfully different at this sample size.
Cite this
Free to cite and reuse with a link back. Data is updated as new runs and prices come in, so include the date.
SlopTV. (2026). Image to video leaderboard: AI video models ranked. Retrieved October 23, 2026, from https://sloptv.co/leaderboard/img2video<a href="https://sloptv.co/leaderboard/img2video">Image to video leaderboard: AI video models ranked</a> (SlopTV)Frequently asked
Which AI video model is best at Image to video right now?
As of 23 October 2026, OpenAI Sora 2 by OpenAI ranks #1 on Image to video on SlopTV's benchmark, scoring 5.00/5 across 4 scored runs (±0 at 95% confidence).