Перейти к основному содержанию

GLM-5.1 (Reasoning)

Z AIGLMОткрытые весаMIT · Коммерческое использование

Описание

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.

Дата выхода
2026-04-07
Параметры
754.0B
Длина контекста
200K
Модальности
text

Радар способностей

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

Рейтинги

Домен#МестоОценкаИсточник
Агентные возможности71
46.0
LS
Рейтинг кодинга96
73.0
AA
Общий рейтинг54
79.0
AA
Наука89
72.0
AA

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Biology

GPQANYU + Cohere + Anthropic (2023)86.2%Сам.

General

LiveBench70.2%

Math

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

Индексы оценки AA

(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

Оценки категорий LLM Stats

(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

Цены

Цена ввода$1.38 / 1M токенов
Цена вывода$4.4 / 1M токенов
Смешанная цена (3:1)$2.135 / 1M токенов
Цена чтения кэша$0.26 / 1M токенов
Цена записи кэшаБесплатно

Скорость

Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s

Рейтинг цен провайдеров

Рейтинг цен провайдеров

20 провайдеров

Самый дешевый: ZAIСамый дорогой: GreenPT
ПровайдерВводВывод
1ZAIСамый дешевый
$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 AIОсновной
$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

Сравнение цен разных API-провайдеров для этой модели.

Внешние ссылки