Artificial Analysis Video Models (October 2026)
In October 2026, Wan 3.0 ranks first with 1,158, followed by Utopai X (based on MiniMax H3) (1,152) and MiniMax H3 (1,142). Top 20 of 30 candidates.
Data as of October 2026
| # | Model | Provider | Score |
|---|---|---|---|
| 1 |  Wan 3.0 | Alibaba | 1,158 |
| 2 | UUtopai X (based on MiniMax H3) | Utopai Studios | 1,152 |
| 3 |  MiniMax H3 | MiniMax | 1,142 |
| 4 |  FLUX 3 | Black Forest Labs | 1,127 |
| 5 |  Dreamina Seedance 2.0 | ByteDance | 1,117 |
| 6 | Dreamina Seedance 2.5 | ByteDance | 1,106 |
| 7 | SSkyReels V4 | Skywork AI | 1,086 |
| 8 |  Gemini Omni Flash 1.1 | 1,073 | |
| 9 | AAgnes-Video-2.5 | Sapiens AI | 1,053 |
| 10 | HappyHorse-1.1 | Alibaba | 1,047 |
| 11 | HappyHorse-1.0 | Alibaba | 1,041 |
| 12 |  grok-imagine-video-1.5 | xAI | 1,038 |
| 13 | Wan2.7-260612 | Alibaba | 1,034 |
| 14 | KKling | Kuaishou | 1,020 |
| 15 |  Kling 3.0 1080p (Pro) | KlingAI | 1,000 |
| 16 |  PixVerse V6 | PixVerse | 998 |
| 17 | Veo 3.1 | 969 | |
| 18 | MMAGI-2 Preview | Sand.ai | 964 |
| 19 | Veo 3 Fast | 963 | |
| 20 |  LTX-2.5 Fast | Lightricks | 950 |
How this chart is built
Draws on a leading third-party evaluation programme that measures model capability across standardised test sets. The chart shows its latest published scores.
Positions are renumbered from high to low by this table's own metric, independent of any ranking the source publishes. Figures are the current real data with no manual adjustment; values we cannot obtain show as “—” and are never filled in with estimates.
FAQ
Artificial Analysis Video Models: who ranks #1?
In October 2026, Alibaba’s Wan 3.0 ranks #1 (score: 1,158); Utopai X (based on MiniMax H3) is second (1,152), followed by MiniMax H3 (1,142).
Artificial Analysis Video Models: what are the top 10?
Ranked by score as of October 2026, the top 10 are: 1. Wan 3.0, 2. Utopai X (based on MiniMax H3), 3. MiniMax H3, 4. FLUX 3, 5. Dreamina Seedance 2.0, 6. Dreamina Seedance 2.5, 7. SkyReels V4, 8. Gemini Omni Flash 1.1, 9. Agnes-Video-2.5, 10. HappyHorse-1.1. The full top 20 is in the table on this page.
Artificial Analysis Video Models: where does the data come from, and how often is it updated?
Draws on a leading third-party evaluation programme that measures model capability across standardised test sets. The chart shows its latest published scores. Refreshed when the source publishes; the current data is dated October 1, 2026.