GLM 5.1
GLM 5.1 is an AI model published by 智谱AI, released on 2026-03-27, for Reasoning model, with 75.4B parameters, and 200K context length, requiring about 1.51TB storage, under the MIT License license, with a 95.30 score on AIME 2026.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $1.40/ 1M | $4.40/ 1M |
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | 5m | $0.260/ 1M | $4.40/ 1M |
Benchmark Results
GLM 5.1 currently shows benchmark results led by HLE (13 / 159, score 52.30), AIME 2026 (3 / 15, score 95.30), SWE-Bench Pro - Public (10 / 44, score 58.40). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
General Knowledge
4 evaluationsCoding and Software Engineer
1 evaluationsAI Agent - Tool Usage
4 evaluationsMath and Reasoning
2 evaluationsCompare with other models
- Peer modelGLM 5.1 vs Kimi K2.610 benchmarks
- Earlier versionGLM 5.1 vs GLM-4.78 benchmarks
- Peer modelGLM 5.1 vs DeepSeek-V4-Pro7 benchmarks
- Earlier versionGLM 5.1 vs GLM-57 benchmarks
- Peer modelGLM 5.1 vs MiniMax-M2.74 benchmarks
- Earlier versionGLM 5.1 vs GLM-4.64 benchmarks
Want a custom combination? Open the compare tool
Publisher
Model Overview
GLM 5.1 is an AI model published by 智谱AI, released on 2026-03-27, for Reasoning model, with 75.4B parameters, and 200K context length, requiring about 1.51TB storage, under the MIT License license, with a 95.30 score on AIME 2026.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
