Back
Zhipu

GLM 5

Zhipu, China175/191 correctLast updated Mar 13, 2026Website

GLM 5 by Zhipu achieved an overall score of 90.7% on Appwrite Arena, ranking #6 of 10 benchmarked models. The benchmark tests how well AI models understand Appwrite - the open-source backend platform for authentication, databases, storage, functions, and more. This model answered 175 of 191 questions correctly across categories including Auth, Databases, Functions, Storage, and CLI. During the benchmark it consumed 1,611,698 tokens costing $1.3180, averaging 22.2 tokens per second over 75m 1s. Compare GLM 5 with other LLMs on the Appwrite Arena leaderboard.

Total tokens
1,611,698Input: 1,511,952 Output: 99,746
Total duration
75m 1s
Avg speed
22.2 tok/s
Total cost
$ 1.3180
Cost/1MOverallFoundationAuthDatabasesFunctionsStorageSitesMessagingRealtimeCLI
$0.72Input: $0.72/1M tokens
Output: $2.30/1M tokens		90.7%99.7%93.2%85.4%94%94.5%89%92.7%86.5%84.1%
Deterministic17/17 correct
AI-Judged98% average score