GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
Tested on 22 benchmarks · BenchGecko score 63.1. Top scores: Artificial Analysis · GPQA Diamond (91.7%), OTIS Mock AIME 2024-2025 (91.1%), GPQA diamond (87.9%).
Qwen3 30B A3B Thinking 2507 scores 63.5 (101% as good) at $0.20/1M input · 86% cheaper
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.
Simple factual questions with verified correct answers. Tests accuracy of basic knowledge retrieval. Low scores indicate hallucination.
Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.
- Typetext
- Context1.0M tokens (~524 books)
- ReleasedAug 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.007
Frequently Asked Questions
Related Models
GPT-5.1-Codex-Mini · OpenAIQwen3.6 Plus · Alibaba QwenQwen3 30B A3B Thinking 2507 · Alibaba QwenKimi K2.7 Code · moonshotaiMixtral 8x7B · Mistral AIKey facts · as of 2026-10-05
- GLM 5.3 by z-ai. BenchGecko score 63.1, rank 71 of 312 scored models (normalized average of public benchmark scores).
- List price $1.40 input · $4.40 output per 1M tokens (as of 2026-10-05).
- Sold by 39 providers (as of 2026-10-05): Relace $0.0300 in / $12.00 out · Wafer $0.0700 in / $8.00 out · Wafer $0.10 in / $8.00 out · InferenceNet $0.12 in / $4.40 out · Morph (fp8) $0.13 in / $3.18 out · and 34 more. Every provider
- Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax E (90% more tokens outside English).
How to cite · data as of 2026-10-05
GLM 5.3 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/glm-5-3
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP