Z AI
Released January 19, 2026

GLM 4.7 Flash

GLM 4.7 Flash by Z AI is an open-weight 30B-A3B Mixture-of-Experts model with Multi-head Latent Attention and interleaved thinking for efficient reasoning.

Inputs
Text
Outputs
Text

Model Overview

Capabilities, design details, and architectural traits

GLM 4.7 Flash - Lightweight MoE with Multi-head Latent Attention

GLM 4.7 Flash is Z.AI's (Zhipu AI) open-weight Mixture-of-Experts language model.

Thinking Design

GLM 4.7 Flash supports two explicitly documented thinking controls:

  • Enable Thinking (boolean, default true): Controls whether the model reasons before replying - toggleable per request.
  • Clear Thinking (boolean, default false): Controls whether thinking content is cleared from conversation history between turns - enabling stateless reasoning chains when needed..

Benchmark Performance

Independent evaluations · Artificial Analysis

14.9%
Intelligence

Accuracy & Capability Details

GPQA - Graduate Science58.1%
Humanity's Last Exam7.6%
SciCode - Scientific Coding33.7%
Instruction Following60.8%
Long Context Reasoning41.7%
τ²-Bench - Agentic Tasks98.8%
TerminalBench - System Control22.0%

Compare Models Side-by-Side

Evaluate specifications, pricing, and independent benchmark indices

Model Details
General Info
ProviderZ AIAnthropicAnthropic
Release DateJanuary 19, 2026September 22, 2026September 28, 2026
Knowledge Cutoff--Jun 2026
Context & Limits
Context Window203K
1M
Best Context Window
1M
Best Context Window
Pricing (per 1M tokens)
Input Pricing
$0.07
Best Input Pricing
$4$2
Output Pricing
$0.40
Best Output Pricing
$20$10
Modalities
Inputs
text
textimagefile
textimagefile
Outputs
text
text
text
Benchmarks (0-100)
Intelligence Index10.6
57.6
Best Intelligence Index
56.0
Coding Index---
Agentic Index---
GLM 4.7 Flash
Claude Opus 5.5
Claude Sonnet 5.5

Humanity's Last Exam

Extremely difficult logical reasoning and knowledge.

5%
GLM 4.7 Flash
Humanity's Last Exam
Score: 5%
GLM 4.7 Flash
61%
Claude Opus 5.5
Humanity's Last Exam
Score: 61%
Claude Opus 5.5
55%
Claude Sonnet 5.5
Humanity's Last Exam
Score: 55%
Claude Sonnet 5.5

Long Context Reasoning

Logical reasoning over long context windows.

20%
GLM 4.7 Flash
Long Context Reasoning
Score: 20%
GLM 4.7 Flash
85%
Claude Opus 5.5
Long Context Reasoning
Score: 85%
Claude Opus 5.5
83%
Claude Sonnet 5.5
Long Context Reasoning
Score: 83%
Claude Sonnet 5.5

SciCode Benchmark

Scientific coding and mathematical modeling.

26%
GLM 4.7 Flash
SciCode Benchmark
Score: 26%
GLM 4.7 Flash
67%
Claude Opus 5.5
SciCode Benchmark
Score: 67%
Claude Opus 5.5
61%
Claude Sonnet 5.5
SciCode Benchmark
Score: 61%
Claude Sonnet 5.5

Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.

Explore more from Z AI

Other models by Z AI

Top AI Models

Leading alternatives by intelligence score

View all