跳轉到主要內容

GLM-5.1 (Reasoning)

Z AIGLM開源權重MIT · 商用許可

描述

GLM-5.1 is Z.AI's next-generation flagship foundation model designed for long-horizon agentic engineering tasks. Built on a 754B MoE architecture (40B active parameters), it can work continuously and autonomously on a single task for up to 8 hours, completing the full loop from planning and execution to iterative optimization and delivery. GLM-5.1 achieves state-of-the-art on SWE-Bench Pro (58.4) and demonstrates strong performance across coding, reasoning, and agentic benchmarks. It supports 200K context length, 128K max output tokens, thinking mode, function calling, structured output, context caching, and MCP integration. Overall performance is aligned with Claude Opus 4.6 with particular strengths in sustained execution and complex engineering optimization.

發布日期
2026-04-07
參數規模
754.0B
上下文長度
200K
支援模態
text

能力雷達圖

39
general
54
coding
87
reasoning
60
science
60
agents
0
multimodal

排行榜排名

領域#排名分數來源
智慧體能力模型榜71
46.0
LS
程式碼能力榜96
73.0
AA
通用能力榜54
79.0
AA
科學能力89
72.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

Vending-Bench 2563441.0%自報
BrowseCompOpenAI (2025)79.3%自報
MCP Atlas71.8%自報
TAU3-Bench70.6%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)69.0%自報
CyberGym68.7%自報
SWE-Bench ProPrinceton NLP (2024)58.4%自報
Finance Agent v244.8%
NL2Repo42.7%自報
Toolathlon40.7%自報
FrontierSWE31.0%

Biology

GPQANYU + Cohere + Anthropic (2023)86.2%自報

General

LiveBench70.2%

Math

AIME 202695.3%自報
HMMT 202594.0%自報
IMO-AnswerBench83.8%自報
HMMT Feb 2682.6%自報
Humanity's Last Exam52.3%自報

AA 評測指數

(Artificial Analysis)
Coding Index(Artificial Analysis)
55.8
Intelligence Index(Artificial Analysis)
41.0
Tau2(Sierra + U Toronto + Vector Institute (2025))
1.0
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Ifbench(Google Research (2023))
0.8
Lcr(Artificial Analysis)
0.7
Terminalbench V2 1
0.6
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench Hard(Stanford × Laude Institute (2026))
0.4
Hle(Center for AI Safety + Scale AI (2025))
0.3
Tau Banking
0.1

LLM Stats 分類評分

(LLM Stats (zeroeval))
Agents
100
Reasoning
100
General
100
Physics
90
Biology
90
Chemistry
90
Math
80
Search
80
Safety
70
Code
60
Tool Calling
60
Vision
50
Finance
40

定價

輸入價格$1.38 / 1M tokens
輸出價格$4.4 / 1M tokens
混合價格(3:1)$2.135 / 1M tokens
快取讀取價格$0.26 / 1M tokens
快取寫入價格免費

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

20 個供應商

最便宜: ZAI最貴: GreenPT
供應商輸入輸出
1ZAI最便宜
$0
$0
2FriendliAI
$0
$0
3CrofAI
$0.45
$2.15
4EmpirioLabs AI
$0.825
$3.301
5EBCloud
$0.8571
$3.4286
6302.AI
$0.86
$3.5
7Alibaba (China)
$0.87
$3.48
8LLM Gateway
$0.931
$2.93
9DigitalOcean
$0.975
$4.3
10Wafer
$1
$3.2
11DInference
$1.25
$3.89
12Z AI主要
$1.38
$4.4
13Cortecs
$1.384
$4.348
14OpenCode Go
$1.4
$4.4
15Z.AI
$1.4
$4.4
16OpenCode Zen
$1.4
$4.4
17Zhipu AI
$1.4
$4.4
18Auriko
$1.4
$4.4
19Charm Hyper
$1.52432
$4.79072
20GreenPT
$1.756
$5.518

比較該模型在不同 API 供應商之間的定價。

外部連結