Model rankings
866 models · 5 boards · 2 sources
Best video
Best open model
Best from China
Most voted
Top three open models
kandinsky-5.0-t2v-proKandinsky · #14 overall1,205
wan-v2.2-a14bAlibaba · #20 overall1,126
kandinsky-5.0-t2v-liteKandinsky · #22 overall1,121
This week's changes
gpt-5.2Coding · #5New
GPT-5.1 Codex (high)Intelligence · #7New
DeepSeek V3.2 (Reasoning)Intelligence · #8New
Z-Image TurboImage · #9New
Nova 2.0 Pro Preview (medium)Intelligence · #16New
| Rank | Change | Model | Score | 95% interval | Votes |
|---|---|---|---|---|---|
| 1 | — | veo-3.1-fast-audioClosedGoogle | 1,383 | ±14 | 6,373 |
| 2 | — | veo-3.1-audioClosedGoogle | 1,374 | ±15 | 6,220 |
| 3 | — | veo-3-fast-audioClosedGoogle | 1,361 | ±12 | 23,616 |
| 4 | — | sora-2-proClosedOpenAI | 1,356 | ±17 | 5,466 |
| 5 | — | veo-3-audioClosedGoogle | 1,346 | ±12 | 17,134 |
| 6 | — | sora-2ClosedOpenAI | 1,325 | ±16 | 6,195 |
| 7 | ▲ 1 | veo-3-fastClosedGoogle | 1,254 | ±12 | 13,330 |
| 8 | ▼ 1 | veo-3ClosedGoogle | 1,253 | ±12 | 12,954 |
| 9 | — | ray-3ClosedLuma AI | 1,208 | ±22 | 1,099 |
| 10 | — | veo-2ClosedGoogle | 1,163 | ±14 | 7,271 |
| 11 | — | soraClosedOpenAI | 1,065 | ±13 | 4,614 |
| 12 | — | ray2ClosedLuma AI | 1,063 | ±16 | 5,764 |
| 13 | — | pika-v2.2ClosedPika | 1,007 | ±14 | 6,635 |
Intelligence over time
Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi