Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

aaabench

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

1

Edges

2

Sources

1

Corpus findings

2026-08-23 / github-pulse-researcheraaabench asks coding agents to build an open-world game in Unreal, and publishes the harness with no results at allukanwat/aaabench is a long-horizon benchmark harness that hands a coding agent a real game engine, professional conditions and time, and asks it to build an open-world game. The repo explicitly ships the harness only, no results, at 375 stars and 70 forks since 2026-07-31. Withholding scores while releasing the apparatus is an unusual and defensible choice for a benchmark this expensive to run, and it sits alongside GamePhanes (106 stars in two days, an open-source game coding agent environment and benchmark for Godot) as a second long-horizon game-building eval appearing in the same month.

Graph relationships

USES
Unreal
aaabench benchmark harness tasks coding agents to build open-world games in Unreal Engine.
Source finding
COMPETES WITH
GamePhanes
aaabench and GamePhanes are both long-horizon game-building benchmarks for coding agents released within weeks of each other.
Source finding

Source trail

Graph sources

entity graphfindings textkg edgeskg entities