This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.

Z AI has launched a newer model, GLM 5V Turbo. We suggest considering it instead.

For more information, see comparison of GLM 5V Turbo to other models and API provider benchmarks for GLM 5V Turbo.

GLM-4.6V (Reasoning) logo
Z AI
•

Open weights model

•

Released December 2025

GLM-4.6V (Reasoning) 智能、性能与价格分析

API 服务商基准测试

模型摘要

智能

17
Artificial Analysis Intelligence Index
智能为 4 档中的第 4 档。

速度

63.0
每秒输出 token 数
速度为 4 档中的第 1 档。

输入价格

US$0.30
美元/100 万 token
输入价格为 4 档中的第 3 档。

输出价格

US$0.90
美元/100 万 token
输出价格为 4 档中的第 3 档。

冗长度

无
Intelligence Index 输出 token 数
冗长度在 4 档中的档位未知。

GLM-4.6V (Reasoning) 的智能水平处于领先行列，但价格有些昂贵；比较对象为其他规模相近的开放权重模型。 该模型支持文本和图像输入，可输出文本，上下文窗口为 128k 个 token。

GLM-4.6V (Reasoning) 在 Artificial Analysis Intelligence Index 上的得分为 17，在同类模型中远高于平均水平（中位数：9）。

GLM-4.6V (Reasoning) 每 100 万输入 token 的价格为 $0.30（有些昂贵，中位数：$0.15），每 100 万输出 token 的价格为 $0.90（有些昂贵，中位数：$0.45）。

GLM-4.6V (Reasoning) 的速度为每秒 63 个 token，明显较慢（93）。

推理是

此页面展示该模型的推理版本。

可能还存在非推理版本。

输入模态

支持：文本和图像

输出模态

支持：文本

上下文窗口128k
约 192 页 A4 纸（12 号 Arial 字体）
总参数量108B
活跃参数量12B
推理期间每个 token 启用的参数数量
许可证MIT
模型权重Hugging Face

指标与同类别模型进行比较：

  • 非推理模型 → 仅与其他非推理模型比较
  • 推理模型 → 同时与推理和非推理模型比较
  • 开放权重模型 → 仅与规模类别相同的其他开放权重模型比较：
    • 微型：≤4B 个参数
    • 小型：4B–40B 个参数
    • 中型：40B–150B 个参数
    • 大型：>150B 个参数
  • 专有模型 → 与价格区间相同的专有模型和开放权重模型比较，采用输入/输出价格 3:1 的混合比例：
    • 每 100 万 token <$0.15
    • 每 100 万 token $0.15–$1
    • 每 100 万 token >$1

亮点

智能

Artificial Analysis Intelligence Index · Higher is better

速度

Output tokens per second · Higher is better

每任务成本

Weighted average cost (USD) per Intelligence Index task · Lower is better

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR
Estimate (independent evaluation forthcoming)
Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if the weights are available but commercial use is limited (typically requires obtaining a paid license).

基准测试

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-Briefcase

Agentic knowledge work, Elo

AutomationBench-AA

Agentic SaaS workflows

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.
Reasoning models are indicated by a lightbulb icon

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

开放性指数

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)
Reasoning models are indicated by a lightbulb icon

Intelligence Index 比较

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

成本

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better
Reasoning models are indicated by a lightbulb icon

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index
Reasoning models are indicated by a lightbulb icon

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)
Reasoning models are indicated by a lightbulb icon

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

上下文窗口

Context Window

Context window: tokens limit · Higher is better
Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

速度

按输出速度（每秒 token 数）衡量

Output Speed

Output tokens per second · Higher is better
Reasoning models are indicated by a lightbulb icon

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better
Reasoning models are indicated by a lightbulb icon

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

延迟

按首 Token 延迟（秒）衡量

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time
Reasoning models are indicated by a lightbulb icon

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

端到端响应时间

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better
Reasoning models are indicated by a lightbulb icon

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).

模型规模（仅开放权重模型）

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference
Reasoning models are indicated by a lightbulb icon

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

常见问题

关于 GLM-4.6V (Reasoning) 的常见问题

GLM-4.6V (Reasoning) 发布于 2025年12月8日。

GLM-4.6V (Reasoning) 由 Z AI 开发。

GLM-4.6V (Reasoning) 在 Artificial Analysis Intelligence Index 上的估算得分为 17，在其他规模相近的开放权重模型中远高于平均水平（中位数：9）。

GLM-4.6V (Reasoning) 以每秒 63.0 个 token 的速度生成输出（基于提供该模型的各服务商中位数），与其他规模相近的开放权重模型相比处于末段（中位数：93.2 t/s）。

GLM-4.6V (Reasoning) 的首 Token 延迟（TTFT）为 4.67 秒（基于提供该模型的各服务商中位数），与其他规模相近的开放权重模型相比处于较高水平（中位数：1.80 秒）。

GLM-4.6V (Reasoning) 每 100 万输入 token 的价格为 $0.30（优于平均水平，中位数：$0.40），每 100 万输出 token 的价格为 $0.90（略高于平均水平，中位数：$0.71）；基于提供该模型的各服务商中位数。

GLM-4.6V (Reasoning) 每 100 万输入 token 的价格为 $0.30，每 100 万输出 token 的价格为 $0.90（基于提供该模型的各服务商中位数）。按缓存命中/输入/输出为 7:2:1 的比例计算，混合价格为每 100 万 token $0.36。价格可能因服务商而异。 比较服务商价格

是，GLM-4.6V (Reasoning) 是推理模型。它会在给出答案之前，通过扩展思考或思维链推理来解决复杂问题。

GLM-4.6V (Reasoning) 支持文本和图像输入。

GLM-4.6V (Reasoning) 支持文本输出。

是，GLM-4.6V (Reasoning) 支持图像输入，可以分析、描述图像并回答有关图像的问题。

是，GLM-4.6V (Reasoning) 是多模态模型，可以处理文本和图像输入并生成文本输出。

GLM-4.6V (Reasoning) 的上下文窗口为 130k 个 token。这决定了模型在单次请求中可以处理多少文本和对话历史。

是，GLM-4.6V (Reasoning) 是开放权重模型，其模型权重已公开，可供下载并自行托管。

GLM-4.6V (Reasoning) 有 108B 参数（启用 12B）。

GLM-4.6V (Reasoning) 是混合专家（MoE）模型，总参数量为 108B，但推理期间仅启用 12B。

GLM-4.6V (Reasoning) 基于 MIT 许可证发布，该许可证允许商业使用。 查看许可证

GLM-4.6V (Reasoning) 在 Artificial Analysis Intelligence Index 上的得分为 17。这项综合基准测试评估模型的推理、知识、数学和编程能力。

是，可通过 2 家服务商的 API 使用 GLM-4.6V (Reasoning)。 比较 API 服务商

可通过 2 家 API 服务商使用 GLM-4.6V (Reasoning)。 比较服务商