ZMIME
OpenAI · video model · Release date unconfirmed

Sora

Sora is a video model from OpenAI. It handles text to video.

  • Video model
  • Proprietary
  • Text to video
Arena score
1,069#47 of 50 · text to video
Starting price
—Not published
Longest clip
—Not published
Resolution
—Audio unconfirmed
Quality & price

How it rates and what it costs

Text to video arena
1,069 ±16#47 of 50 · 4,082 votes

Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Nov 9, 2026.

Specifications

The details

Lab
OpenAI
Type
Video model
Released
—
Inputs
Text prompts
Output
Video
Can do
Text to video
Weights
Proprietary
Availability
Not on the API hosts we track

Arena listing

Same lab

More video models from OpenAI

Questions

About Sora

How good is Sora?

In blind side-by-side votes, Sora scores 1,069 for text to video (#47 of 50). Higher is better; scores within about 32 points of each other are effectively tied.

Who makes Sora?

Sora is a video model from OpenAI.

What can Sora do?

Sora accepts text prompts and produces video. In practice: text to video.

Is Sora open source?

No. Sora is proprietary; you use it through an API or partner apps.

Where can I use Sora?

None of the API hosts we track list it yet.