Santiago @svpino · 03 Sep 2026
Today, we’re releasing SpeedrunBench: the first benchmark that measures how fast agents can beat video games. We asked frontier models not to simply complete video games, but to speedrun them - across 10 titles like Mario Kart and Pokemon. On simpler games, agents get close to https://t.co/XAv83bmREA
111 767Views
85Likes
15Reposts
8Replies
14Quotes
0Bookmarks
Is that a lot?
8.49×vs this author's median13 168 views is typical
80Percentile for this authorof 5 recent posts
18.9×vs 100K–1M median5 930 views is typical
24.54%Reachviews ÷ followers
0.11%Engagement rateof viewers reacted