GameHorizon benchmark tests 47 models across AAA games; planning remains the key bottleneck

yshan2u · x · 2026-09-22

Researchers release GameHorizon Suite, a unified data and evaluation benchmark spanning AAA games, multiple temporal horizons and model families for VLMs, UMMs, GUI, coding and game agents. Aligning videos with auto-annotated operations, goals and strategies, they evaluate 47 models offline and 12 online: future-action planning and goal decomposition remain bottlenecks, and stronger offline performance generally predicts better live gameplay.

Related event: Tencent Releases GameHorizon Benchmark for AI Game-Playing(3 posts)→

Original post →

More from Research

Research channel →