Muse Spark 1.1 Leads Medical Benchmark

Daisy4ai · x · 2026-07-14

On HealthBench Pro (OpenAI's benchmark of 525 real-world clinical tasks), Muse Spark 1.1 performs similarly to GPT-5.6 Sol, with an overall score that is even slightly higher.

The original post highlights that its length-adjusted score is basically on par with GPT-5.6 Sol, but at a much lower reasoning cost: input/output is about $1.25/$4.25 per million tokens, compared to $5/$30 for GPT-5.6 Sol, making the output side roughly 7 times cheaper. The author sets "affordable medical superintelligence" as the ultimate goal.

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 →