---
format: "aidr-story-markdown/v1"
id: "4988fdcb45510e88ccfa1ea727a2fa304f31529db3a4ee7d0c8c095ee11fb50e"
canonical_url: "https://aidr.today/4988fdcb?lang=en"
title: "GLM-5.3 Ranks 2nd Open Weight Model on Terminal Bench After 19 Spot Jump"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-20T05:48:40.000Z"
category: "Models"
topics: ["llm","benchmark","open-source"]
source_urls: ["https://huggingnews.com/ai/update-glm-53-ranks-2nd-open-weight-model-on-terminal-bench-after-19-spo-33d00b52","https://x.com/ValsAI/status/2090192848780136668","https://x.com/ValsAI/status/2090192851057696924","https://x.com/ValsAI/status/2090192853033275460","https://x.com/ValsAI/status/2090192857902841931"]
summary: "The GLM-5.3 model from Z AI scored 71.5% on Terminal-Bench 2.1, placing it second among open-weight models behind Kimi K3. The model also earned an 84.8% on LegalBench, the third-highest score for an open-weight model behind Kimi K3 and MiniMax M3, where it performed most effectively on conclusion and issue-spotting tasks. The Terminal Bench ranking reflects a 19 spot climb from GLM 5.2, with the cost per test falling $0.12 to $0.31. ValsAI noted that current export control restrictions limited evaluations to public and academic benchmarks, and plans to run the Vals Index and Finance Agent benchmarks once the model weights are released."
---

# GLM\-5\.3 Ranks 2nd Open Weight Model on Terminal Bench After 19 Spot Jump

> [Open the canonical story](<https://aidr.today/4988fdcb?lang=en>)

**Published:** 2026-08-20T05:48:40.000Z
**Category:** Models
**Topics:** llm, benchmark, open\-source

## Summary

The GLM\-5\.3 model from Z AI scored 71\.5% on Terminal\-Bench 2\.1, placing it second among open\-weight models behind Kimi K3\. The model also earned an 84\.8% on LegalBench, the third\-highest score for an open\-weight model behind Kimi K3 and MiniMax M3, where it performed most effectively on conclusion and issue\-spotting tasks\. The Terminal Bench ranking reflects a 19 spot climb from GLM 5\.2, with the cost per test falling $0\.12 to $0\.31\. ValsAI noted that current export control restrictions limited evaluations to public and academic benchmarks, and plans to run the Vals Index and Finance Agent benchmarks once the model weights are released\.

## Sources

- [Story source](<https://huggingnews.com/ai/update-glm-53-ranks-2nd-open-weight-model-on-terminal-bench-after-19-spo-33d00b52>)
- [Story source](<https://x.com/ValsAI/status/2090192848780136668>)
- [Supporting source](<https://x.com/ValsAI/status/2090192851057696924>)
- [Supporting source](<https://x.com/ValsAI/status/2090192853033275460>)
- [Supporting source](<https://x.com/ValsAI/status/2090192857902841931>)