Together AI's GLM 5.2 leads on output speed and latency

Together AI has announced that its GLM 5.2 model has achieved the top ranking on Artificial Analysis for both output speed and latency. This positions GLM 5.2 as a leading model in terms of performance metrics within the inference and open-source landscape. AI

IMPACT Sets a new benchmark for inference speed and latency in open-source models.

RANK_REASON This is a performance announcement for an open-source model hosted on a cloud platform, not a release from a frontier lab.

Read on X — Together (inference / OSS) →

• Artificial Analysis
• GLM-5.2
• Together AI

• model release
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →