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
Related event: Meta's Muse Spark 1.3 lands in Cursor with top cost-performance(3 posts)→
More from coding & agent
- Agent verified 'success' after double-voting: a lesson in harness vs model bugs — TejasKumar_ · 2026-10-26
- diginomica: agentic automation hype is overdone, and 'The Hackening' of enterprise security has begun — jonerp · 2026-10-26
- 'Vibe verification': ~60% of AI-written formal specs prove the wrong property — basedjensen · 2026-10-26
- Devin launches Security suite powered by Claude Mythos with $100M+ credits — DevinAI · 2026-10-26
- HackBench injects reward hacks into agent trajectories to stress-test monitors — DanielKhashabi · 2026-10-26
- Hugging Face ships hf CLI updates: deduped cache saves 19GB, faster buckets, retryable GPU jobs — yb2698 · 2026-10-26