Model rankings
1035 models · 5 boards · 2 sources
Best video
Best open model
Best from China
Most voted
Top three by Score
veo-3.1-audio-1080pGoogle1,381
veo-3.1-fast-audio-1080pGoogle1,378
sora-2-proOpenAI1,367
Top three open models
kandinsky-5.0-t2v-proKandinsky · #24 overall1,179
hunyuan-video-1.5Tencent · #25 overall1,171
wan-v2.2-a14bAlibaba · #28 overall1,130
This week's changes
GPT-5.3 Codex (xhigh)Intelligence · #2New
gpt-5.3-codex (codex-harness)Coding · #13New
Qwen3.5 27B (Reasoning)Intelligence · #19New
Qwen3.5 122B A10B (Reasoning)Intelligence · #22New
qwen3.5-122b-a10bCoding · #22New
| Rank | Change | Model | Score | 95% interval | Votes |
|---|---|---|---|---|---|
| 1 | — | veo-3.1-audio-1080pClosedGoogle · 1 more variant | 1,381 | ±16 | 5,537 |
| 2 | — | veo-3.1-fast-audio-1080pClosedGoogle · 1 more variant | 1,378 | ±14 | 5,743 |
| 3 | — | sora-2-proClosedOpenAI | 1,367 | ±9 | 18,963 |
| 4 | — | grok-imagine-video-720pClosedxAI | 1,358 | ±9 | 33,739 |
| 5 | — | veo-3-fast-audioClosedGoogle | 1,351 | ±11 | 25,765 |
| 6 | — | sora-2ClosedOpenAI | 1,342 | ±8 | 25,157 |
| 7 | — | veo-3-audioClosedGoogle | 1,341 | ±12 | 19,331 |
| 8 | — | veo-3ClosedGoogle | 1,257 | ±11 | 15,176 |
| 9 | — | veo-3-fastClosedGoogle | 1,251 | ±12 | 15,453 |
| 10 | — | runway-gen-4.5ClosedRunway | 1,214 | ±11 | 3,932 |
| 11 | — | ray-3ClosedLuma AI | 1,204 | ±23 | 1,057 |
| 12 | — | veo-2ClosedGoogle | 1,166 | ±16 | 7,098 |
| 13 | — | soraClosedOpenAI | 1,071 | ±14 | 4,516 |
| 14 | — | ray2ClosedLuma AI | 1,066 | ±17 | 5,609 |
| 15 | — | pika-v2.2ClosedPika | 1,011 | ±15 | 6,495 |
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