跳轉到主要內容

GLM-4.7 (Reasoning)

Z AIGLM開源權重MIT · 商用許可

描述

GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better terminal and multilingual coding, and a noticeable jump in UI output quality for modern, clean webpages and slides. You can use it in popular coding agents, call it via the Z.ai API, and even run it locally with public weights on HuggingFace and ModelScope using vLLM or SGLang.

發布日期
2025-12-22
參數規模
358.0B
上下文長度
205K
支援模態
text

能力雷達圖

70
general
50
coding
80
reasoning
77
science估算
60
agents
0
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

暫無排名資料

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

General

Tau-bench87.4%自報

Language

MMLU-Pro84.3%自報

Math

AIME 202595.7%自報
IMO-AnswerBench82.0%自報

Reasoning

GPQANYU + Cohere + Anthropic (2023)85.7%自報
LiveCodeBench v684.9%自報
SWE-Bench Verified73.8%自報
SWE-bench Multilingual66.7%自報
BrowseComp-zh66.6%自報
BrowseCompOpenAI (2025)52.0%自報
Humanity's Last Exam42.8%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)41.0%自報
Terminal-Bench33.3%自報

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

(LLM Stats (zeroeval))
Physics
90
Biology
90
Chemistry
90
Language
80
Legal
80
Math
80
Finance
80
Healthcare
80
Reasoning
70
Frontend Development
70
General
70
Search
60
Tool Calling
60
Agents
50
Code
50
Vision
40

定價

輸入價格$0.525 / 1M tokens
輸出價格$2.1 / 1M tokens
混合價格(3:1)$0.7375 / 1M tokens
快取讀取價格$0.11 / 1M tokens
快取寫入價格免費

速度

Tokens/秒44.8
首Token延遲1.39s
首回答延遲46.08s

供應商價格排行

供應商價格排行

2 個供應商

最便宜: DeepInfra最貴: Z AI
供應商輸入輸出
1DeepInfra最便宜
$0.4
$1.75
2Z AI主要
$0.525
$2.1

比較該模型在不同 API 供應商之間的定價。

外部連結