Muse Spark 1.1 Tops Multiple Benchmarks

alexandr_wang · x · 2026-07-09

The post states that Meta's Muse Spark 1.1 achieves SOTA on Harvey Legal Bench, TaxEval, and MedScribe, outperforming Fable on certain tasks. The quoted content adds that the model is faster and cheaper than Fable 5 on these benchmarks, while also taking first place on the legal agent benchmark.

Related event: Meta Launches Muse Spark 1.1: A Low-Cost, High-Performance Agentic Model(133 posts)→

Original post →

More from Models

Models channel →