WHAT NEW IN X11.03 TUE

X 上的 AI 合集档案 · 22 个合集 · 65,263 条

agentVIDEO

Nunu AI 发布 GameGym 游戏 Agent 基准

Nunu AI 开放内部评测环境 GameGym,用通关率和速通速度两个指标衡量前沿模型在电子游戏上的表现。

Jan Schnyder
@jjschnyder26 天前收录原推发布于 2026.10.06
Jan Schnyder @jjschnyder原推发布于 2026.10.06
在 X 上打开原推

Introducing GameGym: The ultimate gaming benchmark for AI agents 🎮 Today we're releasing parts of our internal evaluation environments to track frontier model performance on video games. It measures two main KPIs: completion rate and speed. Similar to speedrunning, while completion rates may eventually saturate, speed is designed to be an evergreen metric for continuously measuring improvements. Games are amongst the hardest challenges for AI to master: 3D, real-time, long-horizon, non-deterministic and massively diverse environments. We believe it is the perfect benchmark built for the endgame. Check out early results here: https://evals.nunu.ai/benchmarks/game-gym

x.com/jjschnyder/status/2107486567610675483采集于 2026.10.07 10:25