GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Tested on 34 benchmarks · BenchGecko score 64.4. Top scores: Chatbot Arena Elo · Coding (1593.3%), Chatbot Arena Elo · Overall (1471.0%), GPQA diamond (92.9%).
Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.
Real-world software engineering tasks from GitHub issues. Models must diagnose bugs and write patches that pass test suites. Human-verified subset of SWE-bench.
LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.
Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.
Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
- Typetext
- Context1.0M tokens (~524 books)
- ReleasedJun 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.007
Frequently Asked Questions
Related Models
Claude Haiku 5.5 · AnthropicKimi K3 · moonshotaiGemini 3.7 Flash · Google DeepMindGPT-5.4 · OpenAIFalcon 2 11B · TIIKey facts · as of 2026-11-11
- GLM 5.2 by z-ai. BenchGecko score 64.4, rank 57 of 326 scored models (normalized average of public benchmark scores).
- List price $0.0070 input · $6.80 output per 1M tokens (as of 2026-11-11).
- Sold by 32 providers (as of 2026-11-11): Relace (fp4) $0.0066 in / $7.98 out · Wafer (fp4) $0.0070 in / $6.80 out · Cloudflare $0.19 in / $8.00 out · Wafer (fp4) $0.19 in / $8.00 out · DeepInfra (fp4) $0.45 in / $1.44 out · and 27 more. Every provider
- Gecko Tests · Gecko Score 25 (rank 51): Who Are You D (Sometimes says it is Google) · Knowledge Horizon D (Knows news up to Feb 2025) · Tokenizer Tax D (70% more tokens outside English).
How to cite · data as of 2026-11-11
GLM 5.2 · benchmarks, pricing and providers. BenchGecko, data as of 2026-11-11. https://benchgecko.ai/model/glm-5-2
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