SpeedrunBench: first benchmark measuring how fast AI agents beat games
mariyaivasileva · x · 2026-09-04
PatronusAI released SpeedrunBench, the first benchmark measuring not whether agents can beat video games but how fast — across 10 titles including Mario Kart and Pokemon.
Results are split: on simpler games, frontier models approach the human world record; on complex ones like Pokemon Blue, the best models (Kimi-K3 and Opus 5) remain 4x off the world record. Benchmark, paper, and demo are public.
More from Models
- Every's Vibe Check: GPT-6 Astra Is a Big Upgrade, but Anthropic's Fable Still Has Better Product Instincts — every · 2026-09-04
- GPT-6 Astra Nukes ARC-AGI-3: Score Jumps from 8% to 63%, 98.6% with Adapter — haider1 · 2026-09-04
- Sam Altman Officially Launches GPT-6 Astra, Claiming Best-in-World Computer Use and Coding — eyishazyer · 2026-09-04
- OpenAI claims GPT-6 Astra SOTA on FrontierMath Tier 4, ARC-AGI 3, TerminalBench-4.0 — dair_ai · 2026-09-04
- Five releases in 48 hours: GPT-6 Astra, Fable 5.1, Gemini 3.8 Flash and more — dr_cintas · 2026-09-04
- Matthew Bellerman Tests GPT-6 Astra Early: 'The Best Model I've Ever Used, Period' — every · 2026-09-04