GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
Tested on 7 benchmarks · BenchGecko score 72.3. Top scores: Chatbot Arena Elo — Overall (1411.3%), OpenCompass — AIME2025 (85.8%), OpenCompass — IFEval (85.4%).
MiniMax M2 scores 72.4 (100% as good) at $0.30/1M input · 50% cheaper
OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.
OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.
OpenCompass MMLU-Pro evaluation. Harder knowledge test with more answer choices.
OpenCompass evaluation of GPQA Diamond. PhD-level science questions from the hardest subset.
OpenCompass evaluation of Humanitys Last Exam. Expert-level cross-discipline knowledge test.
- Typetext
- Context131K tokens (~66 books)
- ReleasedJul 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.003
Frequently Asked Questions
Related Models
MiniMax M2 · minimaxClaude Opus 4.8 · AnthropicQwen2.5 Coder 32B Instruct · Alibaba QwenHermes 3 70B Instruct · nousresearchMuse Spark · UnknownKey facts · as of 2026-10-05
- GLM 4.5 by z-ai. BenchGecko score 72.3, rank 32 of 312 scored models (normalized average of public benchmark scores).
- List price $0.60 input · $2.20 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): Z.AI (fp8) $0.60 in / $2.20 out.
How to cite · data as of 2026-10-05
GLM 4.5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/glm-4-5
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