Muse Spark 1.1 Leads Medical Benchmarks

alexandr_wang · x · 2026-07-14

Muse Spark 1.1 is hailed as the SOTA on HealthBench Professional.

The cited content compares it to GPT-5.6 Sol: Muse Spark 1.1 scores higher overall. While their length-adjusted scores are statistically similar, Muse Spark 1.1 boasts lower inference costs, with output pricing being roughly 7 times cheaper ($1.25/$4.25 vs $5/$30 per M tokens in/out).

Related event: Meta Muse Spark 1.1 Benchmarks Released, Showing Strength in Medical and Agentic Tasks(7 posts)→

Original post →

More from Models

Models channel →