What is the best AI text-to-video model?

Based on blind community voting, Wan 2.6 is currently the #1 ranked AI text-to-video model with an Elo rating of 1249. Rankings update in real time as new votes come in.

How are AI text-to-video models ranked on Lumenfall?

Lumenfall Arena ranks AI models through blind community voting. In each matchup, two models generate from the same prompt and voters pick the better result without seeing model names. Votes are processed using TrueSkill, a Bayesian rating algorithm developed by Microsoft Research, that produces a single Elo score reflecting each model's relative quality.

What is an Elo rating for AI models?

An Elo rating is a numerical score representing a model's skill relative to other models. Under the hood, Lumenfall uses TrueSkill, which tracks two values per model: mu (estimated skill) and sigma (uncertainty). The displayed Elo is calculated as 1000 + 10 x (mu - 3*sigma), a conservative lower bound. A model must prove itself consistently across many matchups to earn a high rating.

Best AI Models for Human Fidelity

Human Fidelity · Text-to-Video

Elo rankings from blind votes across 3 challenges in this category.

Highlights

10 images

Price · Performance

Best models, by

Every ranked model plotted by price against its Elo. The upper-left frontier is the best value: top quality at the lowest cost.

Best Text-to-Video Models by Price

Best AI Models for Human Fidelity

7 models ranked · Last update: October 1, 2026 12:10 AM

#	Model	Price	¢/img	Elo
1	Wan 2.6 Alibaba	$$	3¢	1249
2	Kling V3 Kuaishou	$$$$	8.4¢	1239
3	Seedance 2.0 ByteDance	$$$$	13.6¢	1228
4	P-Video PrunaAI	$$	2¢	1212
5	Sora 2 Pro OpenAI	$$$$	30¢	1211
6	Grok Imagine Video xAI	$$$	5¢	1183
7	Veo 3.1 Fast Google	$$$$	10¢	1151

Wan 2.6 leads the category with a 1249 Elo, outperforming overall leaderboard favorites by offering a 65.6% win rate at nearly a third of the price of Kling V3. While Kling V3 maintains a slightly higher individual win rate of 67.6%, Wan 2.6 establishes a significant value lead in human fidelity over premium-priced models like Sora 2 Pro and Seedance 2.0.

Think a model is ranked wrong? Cast your vote

Highlighted challenges

Text-to-Video Human Fidelity Temporal Consistency

The Rubik's Gauntlet

This prompt is one of the hardest single tests for 2026 SOTA video models because it simultaneously demands extreme fine-motor precision at high speed, long-term physical consistency (the cube must genuinely solve without morphing), and complex multi-element rendering (hyper-detailed skin, sweat, glossy reflections, and dynamic camera movement). Areas where even top models still frequently break down.

Text-to-Video Lighting, Shadows & Materials Scenes & Atmospherics

Neon Rain Reverie

This prompt is exceptionally difficult because it combines complex fluid dynamics (rain, splashing, clinging wet fabric), advanced material simulation (flowing silk + hair in wind), and atmospheric lighting; three areas where even top 2026 models still frequently produce artifacts or unrealistic behavior.

View all challenges

Keep the arena honest

Cast your vote

Pick winners in blind matchups. Every vote nudges the Elo and shapes these rankings.

Cast Your Vote

Suggest a prompt

Got an idea worth testing? Submit a prompt and watch the models battle it out.

Vote Now

Models · slot A

Human Fidelity · Text-to-Video

Highlights

Best models, by

Best Text-to-Video Models by Price

Best Text-to-Video Models by Speed

Best AI Models for Human Fidelity

Highlighted challenges

The Rubik's Gauntlet

Neon Rain Reverie

Cast your vote

Suggest a prompt