Muse Spark 1.1 Nears Top Models in Benchmarks
alexandr_wang · x · 2026-07-12
Muse Spark 1.1 was benchmarked against several frontier models, showing it rivals Grok 4.5 on multiple high-signal evaluations and scores 51 on the Artificial Analysis Intelligence Index.
The post notes an 8-point jump from Muse Spark 1.0 over three months, driven mainly by science reasoning, coding, and knowledge. However, it still trails leaders in agentic knowledge work. Meta also granted the author early access for testing prior to the official release.
Related event: Meta Muse Spark 1.1 Shines Across Multiple Benchmarks(13 posts)→
More from Models
- Claim says Kimi was distilled from Fable, sparking a model-attribution jab — cephaloform · 2026-07-22
- Gemini 3.6 Flash is now available in Antigravity and chat — MartianOnJupiter · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Macaron V1 adds LoRA RL on GLM 5.2 and claims SOTA benchmark gains — Xianbao_QIAN · 2026-07-22