Benchmark Almanac

UI-TARS 15 Games Collection

UI-TARS-2 59.8 Dropped

GUI agents play 15 browser games such as 2048, Infinity-Loop and Snake-solver from screenshots. Each game score is divided by a human score, and the mean is reported.

In-house suite from the UI-TARS-2 report. Human performance is 100 by construction.

Made by ByteDance Seed Released Sep 2025 Video games Tasks kept private Last in a launch post Sep 2025 , dropped before it saturated Last model added Sep 2025
Level
Everyday Most adults, without training
Scored
Settled by events Predictions are scored against what later happens.
Answers
Agent task Many steps in a terminal, browser, desktop, app, game or robot.
1
Model scored in lab cards
1
Launch post lists it, from 1 lab

UI-TARS-2 leads with 59.8

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 1 UI-TARS-2 59.8
#ModelScoreSettingDateSource
1 UI-TARS-2 59.8 Sep 2025 Model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card
59.8 59.8

No launch post has listed it since Sep 2025

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

ByteDance Seed
DateLaunch postScoreAs the post writes it
2 Sep 2025 UI-TARS-2 59.8 15 Games Collection, Mean Normalized Score (UI-TARS-2-RL)

More in Games and long tasks

All 68 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6 Astra 100%
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Scores come from in-game progress or outcomes per title. Nemotron 3 Nano 4B 22.9
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. Gemini 3 Flash 41.9%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. Measures game progress and harmful actions per 100 steps. Muse Spark 2.40