Skip to main content
Video modelLegacy

Sora 2

OpenAI

Released
September 2025
Data date
August 24, 2026

Category view

Position within the category

This overview uses only published data from matching cohorts. Missing values never change a rank.

Text-to-video and image-to-video remain separate. Their input tasks differ, so they do not receive a combined overall rank.

LMArena Text to Video1,340.08 EloRank 11 of 20

Leaderboard

1Gemini Omni Flash1,511.57 Elo
2FLUX.3 Video1,494.42 Elo
3Dreamina Seedance 2.0 720p1,481.72 Elo
10Wan 2.71,344.44 Elo
11Sora 2, Current model1,340.08 Elo
12Wan 2.61,329.84 Elo
20Pika 2.21,007.67 Elo

Measurements

Comparable benchmark results

Each chart contains exactly one source, one measurement series, and one stored comparison cohort. Bars show the position. The measured value appears on the right.

LMArena Text to Video

1,340.08 Elo · Rank 11 of 20

Task: LMArena Text to Video · Sample: 62,692 · Data date: August 26, 2026

1.Gemini Omni Flash1,511.57 Elo
9.Grok Imagine Video1,345.38 Elo
10.Wan 2.71,344.44 Elo
11.Sora 2, Current model1,340.08 Elo
12.Wan 2.61,329.84 Elo
13.PixVerse V5.61,239.73 Elo
20.Pika 2.21,007.67 Elo

7 of 20 model versions shown in this chart. A higher value ranks first.

Source: LMArenaParticipants: 20

Profile

Specifications and access

Published information about this model. Unknown values are not estimated.

Weights
ProprietarySource
Access
APISource
Maximum resolution
720pSource
Maximum duration
20 sSource
Native audio
YesSource

Pricing

Published prices

Prices remain tied to their documented unit and source.

Representative price
$6 per generated minuteSource
fal.ai (fal-ai/sora-2/text-to-video)
$0.8 per request (estimated)Source

Head-to-head comparisons

Compare this model

Each matchup compares this model with exactly one other model from the same category.

More models

Models from the same selection

All AI models

Evidence

Primary sources and data date

Every statement links to its underlying documentation or leaderboard.