NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/GLM 4.7
z-ai logo

GLM 4.7

by z-ai · Released Dec 2025

Open Source
51.7
avg score
Rank #132
Compare
Better than 58% of all models
Context
205K tokens (~102 books)
Input $/1M
$0.60
Output $/1M
$2.20
Type
text
License
Open Source
Benchmarks
29 tested
Data as of
About

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...

Tested on 29 benchmarks · BenchGecko score 51.7. Top scores: Chatbot Arena Elo — Overall (1441.5%), Chatbot Arena Elo — Coding (1434.5%), OpenCompass — AIME2025 (95.4%).

Looking for similar performance at lower cost?
MiniMax M2.7 scores 51.2 (99% as good) at $0.21/1M input · 65% cheaper
Capabilities
coding
58.0
#55 globally
reasoning
50.7
#78 globally
math
51.8
#114 globally
knowledge
46.6
#152 globally
agentic
3.1
#69 globally
general
10.9
#188 globally
language
63.7
#99 globally
Benchmark Scores
Compare All
Tested on 29 benchmarks · Ranked across 8 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
OpenCompass — LiveCodeBenchV6

OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.

83.8·
LiveBench — Coding

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

73.1·
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

41.7·
reasoningCompare reasoning →
LiveBench — Reasoning

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

59.7·
LiveBench — Data Analysis

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

55.2·
SimpleBench

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

37.2·
mathCompare math →
OpenCompass — AIME2025

OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.

95.4·
OTIS Mock AIME 2024-2025

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

83.3·
LiveBench — Mathematics

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

76.0·
Quick compare:DeepSeek logovs DeepSeek V3.1DeepSeek logovs DeepSeek V3.2 Expminimax logovs MiniMax M2.5
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · z-ai GLM 4.7
Dec 2025
51.7
$0.60/M in205Kctx29 benchmarks
Jan 2026
$0.06/M in(-0.54)200Kctx(-5K)1 benchmark
See the full GLM 4.7 family →
Recently Happened
GLM 4.7 pricing increased 50%
Sep 25, 2026
Similar Models
DeepSeek logo
DeepSeek V3.1
DeepSeek
51.8$0.25/1M
DeepSeek logo
DeepSeek V3.2 Exp
DeepSeek
51.6$0.27/1M
minimax logo
MiniMax M2.5
minimax
51.4$0.27/1M
Links
Info
z-aiPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@z-ai
Source Code
GitHubHugging Face
BenchGecko API
glm-4-7
Specifications
  • Typetext
  • Context205K tokens (~102 books)
  • ReleasedDec 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.003
Available On
z-ai logoz-ai$0.60
Categories
codingreasoningmathknowledgeagenticgenerallanguage
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
DeepSeek logoDeepSeek V3.1
51.8
DeepSeek logoDeepSeek V3.2 Exp
51.6
minimax logoMiniMax M2.5
51.4
OpenAI logoo4 Mini
51.4
GLM 4.7 is an open-source text AI model by z-ai, released in December 2025. It has an average benchmark score of 51.7. Context window: 205K tokens.

Related Models

DeepSeek V3.1 · DeepSeekDeepSeek V3.2 Exp · DeepSeekMiniMax M2.5 · minimaxo4 Mini · OpenAIDeepSeek V3.2 · DeepSeek

Benchmarks

Chatbot Arena Elo — OverallChatbot Arena Elo — CodingOpenCompass — AIME2025OpenCompass — IFEvalOpenCompass — GPQA-Diamond

Related Pages

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

Key facts · as of 2026-10-05

  • GLM 4.7 by z-ai. BenchGecko score 51.7, rank 132 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 7 providers (as of 2026-10-05): DeepInfra (fp4) $0.40 in / $1.75 out · Venice (fp4) $0.40 in / $1.93 out · AtlasCloud (fp8) $0.52 in / $1.85 out · Novita (fp8) $0.54 in / $1.98 out · Google $0.60 in / $2.20 out · and 2 more. Every provider

How to cite · data as of 2026-10-05

GLM 4.7 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/glm-4-7

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