OpenAIVideo modelRetired September 2026

Sora 2

Photoreal video with dialogue and a social app; discontinued in September 2026.

Video Generation

of 18
4.2 pts behind #1

races led

weeks at #1

87.4

score

The 30-second version

OpenAI's video model with native audio and a viral social app. Retired in September 2026.

Key takeaways

Current snapshot · illustrative scores · click any race to watch it

Sora 2Best on each axis

Video Generation

#1 frontierSora 2Wan 2.7Veo 3.1

The distilled version first; open any release for the deeper breakdown.

60-second briefing

Sora 2, explained

AI video summary · placeholder render from the auto-written script

From OpenAI's own guide, distilled

Reasoning models do their own step-by-step thinking; give goals and constraints rather than scripting the chain of thought.
Use the reasoning-effort and verbosity controls instead of prompt tricks to trade depth for speed.
Contradictory instructions waste reasoning tokens; audit system prompts for conflicts.
For agents, define stop conditions and how eager the model should be to keep going without asking.
Structured outputs (JSON schema) beat asking politely for a format.

About OpenAI

Maker of ChatGPT and the GPT series, pursuing general-purpose AI at consumer scale.

Optimising for

Frontier reasoning and math, broad consumer usefulness inside ChatGPT, and tiered models (Astra, Sol, Luna) that trade depth for price and speed.

San Francisco, US · founded 2015

Closest rivals

Sora 2 is 4th in video generation; leader is Seedance 2.0.