---
format: "aidr-story-markdown/v1"
id: "6d61c6ef9913b1355718719c94de5a5156a55a5ea4a20cb08ae052df37c9d952"
canonical_url: "https://aidr.today/6d61c6ef?lang=en"
title: "Z AI’s GLM 5.3 Ties Kimi K3 Intelligence Score Using Unchanged Base Model"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-08-19T05:58:02.000Z"
category: "Models"
topics: ["open-source","agent","coding","benchmark"]
source_urls: ["https://huggingnews.com/ai/update-z-ais-glm-53-ties-kimi-k3-intelligence-score-using-unchanged-base-077718ad","https://x.com/AskVenice/status/2089836129474232793","https://x.com/Zai_org/status/2089816129011098048","https://x.com/ZixuanLi_/status/2089818116498808880","https://x.com/ZixuanLi_/status/2089825696801567014","https://x.com/DesignArena/status/2089816993923059857","https://x.com/ArtificialAnlys/status/2089830890709135426"]
summary: "The Venice platform now provides anonymous access to Z AI's latest large language model along with availability on OpenRouter and the company's own first party API. GLM-5.3 achieved a score of 60 on the Artificial Analysis Intelligence Index, tying Kimi K3 for the highest intelligence rating among open weights models. The model maintains the 753 billion total and 40 billion active parameter count of GLM-5.2, relying on optimized post-training rather than architecture changes to boost performance in cybersecurity and coding. Agentic capabilities rose to an Elo of 1770 on the GDPval-AA v2 evaluation, a 246 point jump that places GLM-5.3 second only to Claude Opus 5. The model is priced at $1.40 per 1 million input tokens and $4.40 per 1 million output tokens, though it is less token efficient than its predecessor, using roughly 18,700 output tokens per task. Z AI expects to release the model weights under an MIT license within the next week."
---

# Z AI’s GLM 5\.3 Ties Kimi K3 Intelligence Score Using Unchanged Base Model

> [Open the canonical story](<https://aidr.today/6d61c6ef?lang=en>)

**Published:** 2026-08-19T05:58:02.000Z
**Category:** Models
**Topics:** open\-source, agent, coding, benchmark

## Summary

The Venice platform now provides anonymous access to Z AI's latest large language model along with availability on OpenRouter and the company's own first party API\. GLM\-5\.3 achieved a score of 60 on the Artificial Analysis Intelligence Index, tying Kimi K3 for the highest intelligence rating among open weights models\. The model maintains the 753 billion total and 40 billion active parameter count of GLM\-5\.2, relying on optimized post\-training rather than architecture changes to boost performance in cybersecurity and coding\. Agentic capabilities rose to an Elo of 1770 on the GDPval\-AA v2 evaluation, a 246 point jump that places GLM\-5\.3 second only to Claude Opus 5\. The model is priced at $1\.40 per 1 million input tokens and $4\.40 per 1 million output tokens, though it is less token efficient than its predecessor, using roughly 18,700 output tokens per task\. Z AI expects to release the model weights under an MIT license within the next week\.

## Sources

- [Story source](<https://huggingnews.com/ai/update-z-ais-glm-53-ties-kimi-k3-intelligence-score-using-unchanged-base-077718ad>)
- [Story source](<https://x.com/AskVenice/status/2089836129474232793>)
- [Story source](<https://x.com/Zai_org/status/2089816129011098048>)
- [Story source](<https://x.com/ZixuanLi_/status/2089818116498808880>)
- [Story source](<https://x.com/ZixuanLi_/status/2089825696801567014>)
- [Supporting source](<https://x.com/DesignArena/status/2089816993923059857>)
- [Supporting source](<https://x.com/ArtificialAnlys/status/2089830890709135426>)