LLM
Meta's Muse Spark 1.1 outperforms GLM-5.2 in coding and costs slightly less
Matthias BastianThe Decoder
AI Summary
Meta's Muse Spark 1.1 has improved significantly, scoring 51 on the Artificial Analysis Intelligence Index and outperforming GLM-5.2 in coding benchmarks with a score of 71.3 at a lower cost of $0.26 per task. The model's hallucination rate has also substantially decreased from 73 to 38 percent.
This article was originally published on The Decoder. Read the full story at the source.
Read Full Article at The DecoderRelated Articles
Anthropic launches Opus 5
TechCrunch AI
Anthropic releases Opus 5 with ‘close’ to Fable 5’s capabilities
The Verge AI
Microsoft's open-weight AI push is so obviously an Azure play it hurts
The Decoder
Sakana claims its AI model router Fugu Ultra v1.1 now beats Fable 5 without even including it in the pool
The Decoder