ModelsAug 20, 2026 · 12:484 sources

GLM-5.3 Ranks 2nd Open Weight Model on Terminal Bench After 19 Spot Jump

From huggingnews.com

Image: huggingnews.com
AI;DR

Z AI's GLM-5.3 model scored 71.5% on Terminal-Bench 2.1, ranking second among open-weight models behind Kimi K3. The model also achieved an 84.8% score on LegalBench, its third-highest score for an open-weight model behind Kimi K3 and MiniMax M3.

Read the sourceSign in to suggest

Sources

+ 3 more
  1. SUPPORT@valsai“At just $0.31/test, it is $0.12 cheaper than 5.2”x.com
  2. SUPPORT@valsai“It is strongest on conclusion and issue-spotting tasks, with interpretation being the weak spot”x.com
  3. SUPPORT@valsai“We look forward to running our private benchmarks such as the Vals Index, Finance Agent, and Vibe Code Bench once the weights become available”x.com

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today