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)→
More from Models
- Claude's refusal to type one-time passwords is a real security impediment — AaronBergman18 · 2026-10-27
- Integrity and refusal may correlate: the fundamental tradeoff behind password refusals — AaronBergman18 · 2026-10-27
- repligate argues context full of noise is genuinely 'hard' for LLMs, mulls an info-theory model of breaks — repligate · 2026-10-27
- Fork builds engine to run Qwen at ~400 tok/s on three used V100s — jfinkpottery · 2026-10-27
- Meta joins frontier labs reporting CoT controllability evals in Muse Spark 1.3 card — tomekkorbak · 2026-10-27
- The tokenizer tax: AI models cost more when you don't use English — postalex · 2026-10-27