Meta's Muse Spark 1.3 Max hits 67.9% on CursorBench at $1.31/task, 4.3x cheaper than GPT-5.6 Sol Max
shuyanzh36 · x · 2026-09-09
Meta's Muse Spark 1.3 Max scored 67.9% on CursorBench 3.2, Cursor's benchmark of ambiguous multi-file tasks from real sessions, at just $1.31 per task — versus 67.2% at $5.69 for GPT-5.6 Sol Max, making it 4.3x cheaper and a new pareto frontier of real usability. The model is now available in Cursor.
Other notable results:
- Fable 5.1 Max tops the chart at 73.4%, but costs $9.64/task
- Grok 4.6 Extra High: 70.8% at $2.81, another strong value pick
- Muse Spark 1.3 comes in multiple tiers: Extra High 63.9% ($1.05), High 61.7% ($0.84), Medium 60.8% ($0.77)
- Kimi K3 Max: 60.8% at $2.70
More from coding & agent
- OpenClaw 2026.9.3 ships: 1,844 PRs, cloud repo work, live browser automation — steipete · 2026-09-09
- Stripe Exec: The Easiest Way to Get Agent-Ready Is Agent-Friendly Checkout — jeff_weinstein · 2026-09-09
- How Cursor's Shipping Velocity Broke GitHub's Moat — and No One Owns SOTA Now — pzakin · 2026-09-09
- Ladybird Browser Ships Big Month: Twitch Playback, JS Debugging, Rust Migration — unixterminal · 2026-09-09
- GitHub's HydraFusion in Copilot CLI Auto-Routes Tasks Across Draft-Critique-Revise — unixterminal · 2026-09-09
- Idea: AI coding tools should pitch app ideas from your unused credits and build them — thisiskp_ · 2026-09-09