Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

WorldArena Track 1 - Controllability — leaderboard

Metric: Score (%). Source: huggingface.co. 124 models tracked.

Top models

#ModelScore
1UNIS91.6
2DexWorldEngine91.03
3ABot-PhysWorld (text)90.84
4MAI90.56
5RevelioWM90.5
6PortkeySim90.47
7Veo3.190.47
8WAI90.44
9PensieveWM90.4
10UBWorld90.38

Interactive version: theaggregate.ai/benchmark?slug=worldarena-track-1-controllability · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.