跳转到主要内容

GLM-4.7 (Reasoning)

Z AIGLM开源权重MIT · 商用许可

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.

发布日期
2025-12-22
参数规模
358.0B
上下文长度
205K
支持模态
text

能力雷达图

49
general
61
coding
93
reasoning
60
science
60
agents
0
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜87
42.0
LS
代码能力榜121
69.0
AA
通用能力榜70
76.0
AA
科学能力96
71.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Tau-bench87.4%自报
BrowseCompOpenAI (2025)52.0%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)41.0%自报
Terminal-Bench33.3%自报

Biology

GPQANYU + Cohere + Anthropic (2023)85.7%自报

Code

SWE-Bench Verified73.8%自报
SWE-bench Multilingual66.7%自报

Finance

MMLU-Pro84.3%自报

General

LiveCodeBench v684.9%自报

Math

AIME 202595.7%自报
IMO-AnswerBench82.0%自报
Humanity's Last Exam42.8%自报

Reasoning

BrowseComp-zh66.6%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
95.0
Coding Index(Artificial Analysis)
45.3
Intelligence Index(Artificial Analysis)
34.5
Tau2(Sierra + U Toronto + Vector Institute (2025))
1.0
Aime 25(MAA (Mathematical Association of America))
0.9
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.9
Lcr(Artificial Analysis)
0.7
Ifbench(Google Research (2023))
0.7
Terminalbench V2 1
0.5
Scicode(UIUC + Argonne National Lab (2024))
0.5
Terminalbench Hard(Stanford × Laude Institute (2026))
0.3
Hle(Center for AI Safety + Scale AI (2025))
0.3
Tau Banking
0.1

LLM Stats 分类评分

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

定价

输入价格$0.6 / 1M tokens
输出价格$2.2 / 1M tokens
混合价格(3:1)$1 / 1M tokens
缓存读取价格$0.11 / 1M tokens
缓存写入价格免费

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

供应商价格排行

10 个供应商

最便宜: CrofAI最贵: Moark
供应商输入输出
1CrofAI最便宜
$0.25
$1.1
2302.AI
$0.286
$1.142
3LLM Gateway
$0.38
$1.98
4DInference
$0.45
$1.65
5Z AI主要
$0.6
$2.2
6Z.AI
$0.6
$2.2
7OpenCode Zen
$0.6
$2.2
8Zhipu AI
$0.6
$2.2
9Cortecs
$0.78
$2.785
10Moark
$3.5
$14

比较该模型在不同 API 供应商之间的定价。

外部链接