Home/Models/GLM 5.1
z-ai logo

GLM 5.1

by z-ai · Released Apr 2026

Open Source
70.4
avg score
Rank #49
Compare
Better than 82% of all models
Context
205K tokens (~102 books)
Input $/1M
$1.40
Output $/1M
$4.40
Type
text
License
Open Source
Benchmarks
22 tested
Data updated today
About

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...

Tested on 22 benchmarks with 59.8% average. Top scores: Chatbot Arena Elo — Coding (1529.2%), Chatbot Arena Elo — Overall (1475.3%), OTIS Mock AIME 2024-2025 (92.2%).

Looking for similar performance at lower cost?
Qwen3.6 Plus scores 69.8 (99% as good) at $0.33/1M input · 77% cheaper
Capabilities
coding
65.4
#30 globally
reasoning
62.1
#45 globally
math
55.8
#71 globally
knowledge
51.5
#111 globally
language
70.1
#76 globally
speed
69.9
#28 globally
Benchmark Scores
Compare All
Tested on 22 benchmarks · Ranked across 7 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

75.4
SWE-Bench verified

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.

74.2
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

57.1
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

72.5
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

63.2
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

50.4
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

92.2
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

84.9
FrontierMath-2025-02-28-Private

Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.

33.5
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
glm-5-1
Specifications
  • Typetext
  • Context205K tokens (~102 books)
  • ReleasedApr 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.007
Available On
z-ai logoz-ai$1.40
Share & Export
Tweet
GLM 5.1 is an open-source text AI model by z-ai, released in April 2026. It has an average benchmark score of 70.4. Context window: 205K tokens.