Benchmark
Camera 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, “camera-dolly-in-door”, 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 | xAI |
5.00 | ±0 | 5.00 | 5.00 | 5.00 | — | — | 1.00 | 85 | — | 4 | |
| 2 | ByteDance |
5.00 | ±0 | 5.00 | 5.00 | 5.00 | — | — | — | 339 | — | 4 | |
| 3 | Runway |
5.00 | ±0 | 5.00 | 5.00 | 5.00 | 5.00 | — | — | — | — | 4 | |
| 4 | PixVerse |
4.97 | ±0.1 | 4.88 | 5.00 | 5.00 | 5.00 | — | — | — | — | 4 | |
| 5 | 4.96 | ±0 | 5.00 | 5.00 | 5.00 | 5.00 | 4.80 | — | — | — | 4 | ||
| 6 | Vivix |
4.88 | ±0.4 | 4.75 | 5.00 | 4.88 | — | — | 1.00 | 10 | $0.107 | 4 | |
| 7 | Kuaishou |
4.79 | ±0.66 | 4.75 | 4.88 | 4.75 | — | — | 1.00 | 190 | — | 4 | |
| 8 | Kuaishou |
4.75 | ±0.51 | 4.63 | 4.88 | 4.75 | — | — | — | — | — | 4 | |
| 9 | Black Forest Labs |
4.71 | ±0.93 | 4.38 | 5.00 | 4.75 | — | — | 1.00 | 98 | $1.360 | 4 | |
| 10 | Kuaishou |
4.70 | ±0.95 | 4.38 | 5.00 | 4.50 | 4.63 | 5.00 | — | — | — | 4 | |
| 11 | Alibaba |
4.67 | ±0.89 | 4.00 | 5.00 | 5.00 | — | — | — | — | — | 4 | |
| 12 | ByteDance |
4.63 | ±1.19 | 4.25 | 4.88 | 4.75 | — | — | — | 233 | — | 4 | |
| 13 | 4.38 | ±1.99 | 4.38 | 4.50 | 4.25 | — | — | — | 131 | — | 4 | ||
| 14 | MiniMax |
4.29 | ±2.25 | 4.25 | 4.50 | 4.13 | — | — | — | 448 | — | 4 | |
| 15 | OpenAI |
4.17 | ±1.67 | 3.63 | 4.63 | 4.25 | — | — | 1.00 | 217 | — | 4 | |
| 16 | MiniMax |
3.63 | ±2.58 | 3.38 | 4.25 | 3.25 | — | — | — | 300 | — | 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.
Genativity. (2026). Camera leaderboard: AI video models ranked. Retrieved October 23, 2026, from https://genativity.com/leaderboard/camera<a href="https://genativity.com/leaderboard/camera">Camera leaderboard: AI video models ranked</a> (Genativity)Frequently asked
Which AI video model is best at Camera right now?
As of 23 October 2026, Grok Video by xAI ranks #1 on Camera on Genativity's benchmark, scoring 5.00/5 across 4 scored runs (±0 at 95% confidence).