Z.ai released GLM-4.7, an updated foundation model with improvements in coding, reasoning, and agentic capabilities, including open-source SOTA performance on benchmarks and enhanced agentic coding.

Model update

How it measures

Artificial Analysis · Intelligence Index · Reasoning

22.2210thof 696 models

Coding index45.3 · 125th

Math index95 · 9th

Median 12.5Top 57.6

Benchmarks, as Artificial Analysis ran them

86%GPQA Diamond
27%Humanity's Last Exam
45%Terminal-Bench 2.1
32%Terminal-Bench Hard
89%LiveCodeBench
95%AIME 2025
96%τ²-Bench
12%τ²-Bench Banking
86%MMLU-Pro
68%IFBench
71%Long context reasoning

Per 1M tokens: $0.60 in · $2.20 out
Context: 205K tokens

LMArena · Text95thof 417· 19th of 227 open models

1Gemini 4 Argon (High)
2Muse Wonder (Max)
3Claude Opus 5.5 (High)
4Claude Fable 5 (High)

glm-4.7 · 1,441 (1,435–1,447) · 12,253 votes

Rated by versionGLMRated 17 points above GLM-4.6; GLM-5.3 rates 39 points higher.

GLM-4.7 · 1,441 (1,435–1,447) · 95th

Against list priceRating for the price

GLM-4.7 · 1,441 · $0.90 per 1M tokens ($0.54 in, $1.98 out) · 205K context

LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 21 October 2026 · Artificial Analysis, read 21 October 2026

About the model

Lab: Z.ai
Variant: GLM-4.7-Flash
Weights: Open
Released: 22 December 2025, per models.dev
OpenRouter: Listed 22 December 2025z-ai/glm-4.7

Ask your AI

Your brief, straight from the record

Connect once, then ask Claude or ChatGPT what changed for the tools you use. Every item links to its page on forck.live.

+ any MCP app

Connect your AI →