Muse Spark 1.1 Beats GLM-5.2 in Coding Eval
The Decoder · rss · 2026-07-11
The Decoder reports that Meta's Muse Spark 1.1 scored 51 on the Artificial Analysis Intelligence Index, marking an 8-point improvement in just three months.
Key data points from the report include:
- For coding tasks, Muse Spark 1.1 scored 71.3, slightly outperforming GLM-5.2.
- The cost per task is approximately $0.26, making it cheaper than its counterparts.
- The hallucination rate dropped from 73% to 38%.
The core takeaway is that the model has made solid progress in coding ability, cost efficiency, and hallucination control.
More from Models
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27
- ICML 2026 position paper: LLM 'thinking traces' are a harmful anthropomorphism — rao2z · 2026-10-27
- One stray 'u' and Claude starts spelling like a Brit — cantrell · 2026-10-27
- Cohere's Invent-A-Dataset paper: zero-seed synthetic data beats frontier APIs on quality and diversity — idanbeck · 2026-10-27
- ARC Prize redesigns leaderboard: highest reasoning effort by default, CSV export — mhmazur · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27