videogamebench/lite-browser
Paused browser game
Observe a frame and act while the environment waits for model reasoning.
screen capturekeyboard control
Not yet importedRequires sandbox
VideoGameBench
Upstream publisher VideoGameBenchalexzhang13/videogamebench
Visual computer-use evaluation across Game Boy, DOS, and browser games, with a paused Lite mode for latency-fair comparison.
simulationcomputer-usevisual-agentssandbox
PROVENANCEUPSTREAM RECORD
- Upstream source
- alexzhang13/videogamebench
- Trunchbull port
- Not packaged
- Version
- LITE
- Release digest
- Not compiled
Source commit: Upstream head not pinnedPublished Indexed July 30, 2026
WHAT THIS PROJECT MEASURES
README
VideoGameBench measures visual perception and control against recognizable games. Lite mode pauses the environment while the model reasons, reducing the degree to which provider latency determines the score.
A public Trunchbull import must separate paused and real-time results and must never redistribute proprietary game assets. Commercial assets need an operator- or user-supplied path.
EXECUTION CONTRACT
Requires visual computer use, game-state reset, recordings, and asset-aware sandbox provisioning.
TRUNCHBULL AVAILABILITY
Import status
Not yet imported
Not yet imported. Start with Lite mode and only environments whose assets can be legally provisioned.
1 CASES
Evaluation cases
1
Requires sandbox
2 REQUESTED TOOLS
Tools
2
screen capture
sandboxProvides the current visual observation.
Required
keyboard control
sandboxSends bounded game inputs to the active environment.
Required
MACHINE-READABLE PROVENANCE
Registry record
{
"name": "VideoGameBench",
"catalogOwner": null,
"source": {
"url": "https://github.com/alexzhang13/videogamebench",
"version": "VideoGameBench Lite candidate",
"commit": "Upstream head not pinned",
"license": "Mixed assets / review required"
},
"port": null,
"release": {
"digest": "Not compiled",
"lane": "sandbox",
"sandboxRequired": true
},
"cases": [
"videogamebench/lite-browser"
],
"tools": [
"screen capture",
"keyboard control"
]
}BUILD ON THIS PROJECT