NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GLM 5.1
z-ai logo

GLM 5.1

by z-ai · Released Apr 2026

Open Source
63.8
avg score
Rank #66
Compare
Better than 79% of all models
Context
205K tokens (~102 books)
Input $/1M
$0.97
Output $/1M
$3.04
Type
text
License
Open Source
Benchmarks
26 tested
Data as of
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 26 benchmarks · BenchGecko score 63.8. Top scores: Chatbot Arena Elo — Coding (1508.5%), Chatbot Arena Elo — Overall (1464.6%), OTIS Mock AIME 2024-2025 (93.3%).

Looking for similar performance at lower cost?
Qwen3 30B A3B Thinking 2507 scores 63.5 (100% as good) at $0.20/1M input · 79% cheaper
Capabilities
coding
65.4
#26 globally
reasoning
60.6
#57 globally
math
53.9
#103 globally
knowledge
51.4
#116 globally
agentic
40.9
#29 globally
general
20.2
#162 globally
speed
41.9
#55 globally
language
70.1
#78 globally
Benchmark Scores
Compare All
Tested on 26 benchmarks · Ranked across 9 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
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·
reasoningCompare reasoning →
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.

46.1·
mathCompare math →
OTIS Mock AIME 2024-2025

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

93.3·
LiveBench — Mathematics

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

84.9·
FrontierMath-Tiers-1-3-v2-Private
36.8·
Quick compare:OpenAI logovs GPT-4 (older v0314)moonshotai logovs Kimi K2.7 CodeMistral AI logovs Mixtral 8x7B
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Recently Happened
GLM 5.1 pricing dropped 23%
Aug 30, 2026
GLM 5.1 pricing increased 30%
Aug 26, 2026
GLM 5.1 pricing dropped 31%
Aug 15, 2026
GLM 5.1 pricing dropped 29%
Jul 3, 2026
GLM 5.1 pricing increased 40%
Jun 30, 2026
GLM 5.1 pricing increased 50%
Apr 22, 2026
Similar Models
OpenAI logo
GPT-4 (older v0314)
OpenAI
63.8$30.00/1M
moonshotai logo
Kimi K2.7 Code
moonshotai
63.6$0.61/1M
Mistral AI logo
Mixtral 8x7B
Mistral AI
63.6n/a
Links
Info
z-aiPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@z-ai
Source Code
GitHubHugging Face
BenchGecko API
glm-5-1
Specifications
  • Typetext
  • Context205K tokens (~102 books)
  • ReleasedApr 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.005
Available On
z-ai logoz-ai$0.97
Categories
codingreasoningmathknowledgeagenticgeneralspeedlanguage
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
OpenAI logoGPT-4 (older v0314)
63.8
moonshotai logoKimi K2.7 Code
63.6
Mistral AI logoMixtral 8x7B
63.6
Meta logoMeta Llama 3 8B
64.0
GLM 5.1 is an open-source text AI model by z-ai, released in April 2026. It has an average benchmark score of 63.8. Context window: 205K tokens.

Related Models

GPT-4 (older v0314) · OpenAIKimi K2.7 Code · moonshotaiMixtral 8x7B · Mistral AIMeta Llama 3 8B · MetaQwen2.5 Coder 14B Instruct · Alibaba

Benchmarks

Chatbot Arena Elo — CodingChatbot Arena Elo — OverallOTIS Mock AIME 2024-2025GPQA diamondLiveBench — Mathematics

Related Pages

z-ai · Providerz-ai · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • GLM 5.1 by z-ai. BenchGecko score 63.8, rank 66 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.97 input · $3.04 output per 1M tokens (as of 2026-10-05).
  • Sold by 13 providers (as of 2026-10-05): StreamLake (fp8) $0.97 in / $3.04 out · Chutes (fp8) $0.98 in / $3.08 out · SiliconFlow (fp8) $1.19 in / $3.74 out · Phala $1.21 in / $4.20 out · AtlasCloud (fp8) $1.26 in / $3.96 out · and 8 more. Every provider
  • Gecko Tests: Who Are You B (Knows who made it) · Tokenizer Tax D (71% more tokens outside English).

How to cite · data as of 2026-10-05

GLM 5.1 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/glm-5-1

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