Generation highlights
How the top models compare
Best models, by
Best Text-to-Vector Models by Price
1 model without pricing omitted.
Best Text-to-Vector Models by Speed
2 models waiting for enough speed data.
Best AI Models for Text-to-Vector
| # | Model | Elo |
|---|---|---|
| 1 | 1257 | |
| 2 | 1224 | |
| 3 | 1174 | |
| 4 | 1150 | |
| 5 | 914 |
As of July 2026, Recraft V4.1 Pro SVG leads the leaderboard with a 1257 Elo and the highest win rate of 88.9%, maintaining a 33-point lead over its predecessor, Recraft V4 SVG (1224 Elo). The top four positions are exclusively held by Recraft AI models, creating a dominant performance gap of over 230 Elo points between the specialist leader and the next closest competitor, OpenAI’s GPT-5.5 (914 Elo). Despite the Pro version’s dominance, Recraft V4.1 SVG offers a significantly more efficient alternative for high-tier performance, delivering a 1174 Elo score at nearly a quarter of the price and twice the generation speed of the top-ranked model.
Highlighted challenges
Capybara Construction Worker
“A Capybara steering an excavator”
Awaiting blind votes
1 model have taken it on, but there aren't enough votes to rank them yet. Open the challenge to see every take.
Recent SOTA shifts in Text-to-Vector
Full historyFAQ
What is the best AI text-to-vector model?
Based on blind community voting, Recraft V4.1 Pro SVG is currently the #1 ranked AI text-to-vector model with an Elo rating of 1257. Rankings update in real time as new votes come in.
How are AI text-to-vector 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.
Keep the arena honest
Cast your vote
Pick winners in blind matchups. Every vote nudges the Elo and shapes these rankings.
Cast Your VoteSuggest a prompt
Got an idea worth testing? Submit a prompt and watch the models battle it out.