Tim Dettmers(@Tim_Dettmers):Trying GLM 5.3 right now. Avg: Prefill ~1 ktok/s, thinking/output ~60 tok/s. In our harness, we already see with full thinking traces GLM 5.2 > Fable+Claude Code. But GLM 5.3 is just on another level. It is very precise and concise. Just testing long-task performance. Exciting!

2026.08.14 13:35

Trying GLM 5.3 right now. Avg: Prefill ~1 ktok/s, thinking/output ~60 tok/s. In our harness, we already see with full thinking traces GLM 5.2 > Fable+Claude Code. But GLM 5.3 is just on another level. It is very precise and concise. Just testing long-task performance. Exciting!

显示更多

Z.ai@Zai_org

2026.08.14 05:17

Introducing GLM-5.3: Built to Code. Ready for Cyber Defense. - Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model - A major leap in cybersecurity, setting a new standard among open models Tech Blog:

显示更多

275

转发到社区