Muse Spark 1.3 shines on brand-new, unoptimizable CursorBench 4.0
jyangballin · x · 2026-09-11
- leerob announced CursorBench 4.0, adding new tasks on instruction following and long-horizon work on challenging projects, and raising difficulty so all models score lower — a benchmark models couldn't have optimized against.
- mattdeitke argued Muse Spark 1.3 performing strongly on this fresh benchmark shows real generalization, countering Meta's old "benchmaxxing" reputation.
Related event: CursorBench 4.0 Launches with Harder Tasks; Fable 5.1 Max Tops the Board(6 posts)→
More from Models
- Tencent releases Hy-SimulMT: real-time speech-to-speech translation with ~3s latency — _akhaliq · 2026-10-28
- Meta's Omnilingual MT covers 1,600 languages, 1B–8B models rival 70B LLMs — kalyan_kpl · 2026-10-28
- Uncensored LFM3-1.7B GGUF weights released on Hugging Face — kalyan_kpl · 2026-10-28
- Token demand on OpenRouter grew 27x to 165T weekly, open models now serve 72% — FinanceYF5 · 2026-10-28
- Tesla Optimus 'robot university' leak: 40-camera mocap suits, 24/7 data ops for months — Scobleizer · 2026-10-28
- Letta's FrontierMemory leaderboard: Letta Dream tops at 73.3%, beating OpenAI and Claude agents — afurgs · 2026-10-28