GLM-5.3
z-ai
Cross-checked
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps. Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Benchmark evidence and ranking method · GLM-5.3
Cross-checked
Terminal-Bench 4.0 · Claude Code · max: 41.82% · 95% CI ± 3.23%
Artificial Analysis · GLM-5.3 (max)
Test configuration: max
Terminal-Bench 2.1: 83.90% · SciCode: 59.03%
LiveBench · 2026-06-25 · glm-5.3
Coding: 78.95% · Agentic Coding: 60.91%
ModelRank assigns editorial tiers using public coding evidence, not automatic index thresholds or statistically proven classes. Price, speed, context size and sponsorship do not affect tiers.
DeepSeek V4 Flash 0731 = 100. The index reflects two shared tests, not capability multiples or statistically established gaps.
Results reflect particular model configurations. Agent harnesses, reasoning effort, tools, budgets and tasks may differ. Close indices do not establish superiority. B describes a relative position in this selected group, not an inability to code.
Data checked: 2026-09-10. Snapshot date is the retrieval date, not necessarily the evaluation date.
Compare with Alternatives
Frequently Asked Questions
What is GLM-5.3's coding score and ranking tier?
GLM-5.3 by z-ai is rated as Tier A+ on ModelRank with a coding score of 111.83 (Reference baseline = 100) as a reference index derived from public benchmark evidence. Tiers are editorial assessments; the index does not establish real-world capability differences.
What is the API pricing and context window for GLM-5.3?
GLM-5.3 features a 1,048,576 token context window. Pricing is $0.039 per 1M input tokens and $4.8 per 1M output tokens (OpenRouter quote).
Try GLM-5.3
Last updated: October 11, 2026