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 Results for other workloads are historical and no longer updated.

Alibaba has launched a newer model, Qwen3 235B (Non-reasoning). We suggest considering it instead.

For more information, see comparison of Qwen3 235B (Non-reasoning) to other models and API provider benchmarks for Qwen3 235B (Non-reasoning).

Alibaba

•

Open weights model

•

Released 2024年9月

Qwen2.5 Instruct 72B 智能、性能与价格分析

立即试用 API 服务商基准测试

智能Updated

Artificial Analysis Intelligence Index

速度

无

每秒输出 token 数

成本

输入 US$0.475输出 US$0.495缓存折扣 25%

无

Intelligence Index 每项任务的成本

冗长度

无

Intelligence Index 输出 token 数

Qwen2.5 Instruct 72B 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非推理模型。该模型支持文本输入，可输出文本，上下文窗口为 131k 个 token。

Qwen2.5 Instruct 72B 在 Artificial Analysis Intelligence Index 上的得分为 8，在同类模型中远高于平均水平（中位数：7）。

Qwen2.5 Instruct 72B 每 100 万输入 token 的价格为 $0.47（昂贵，中位数：$0.14），每 100 万输出 token 的价格为 $0.49（有些昂贵，中位数：$0.40）。

推理	否此页面展示该模型的非推理版本。可能还存在推理版本。
输入模态	支持：文本
输出模态	支持：文本
上下文窗口	131k 约 197 页 A4 纸（12 号 Arial 字体）
总参数量	72B
许可证	Qwen License Agreement
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

Updated

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Updated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Estimate (independent evaluation forthcoming)

Artificial Analysis Intelligence Index v4.3 includes: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench v4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. 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

Estimate (independent evaluation forthcoming)

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

基准测试

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

AA-Briefcase

Agentic knowledge work, (Elo-500)/2000

GDPval-AA v2

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

AutomationBench-AAUpdated

Agentic SaaS workflows

Terminal-Bench v4.0New

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GDP.pdfNew

Professional document reasoning, All-pass

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR v1.1

Long context reasoning

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

IFBench

Instruction following

𝜏³-Banking

Agentic tool use

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

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

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.

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)

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

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.

成本

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

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)

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

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).

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

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 Qwen2.5 Instruct 72B 的常见问题

Qwen2.5 Instruct 72B 发布于 2024年9月19日。

Qwen2.5 Instruct 72B 由 Alibaba 开发。

Qwen2.5 Instruct 72B 在 Artificial Analysis Intelligence Index 上的估算得分为 8，在其他规模相近的开放权重非推理模型中远高于平均水平（中位数：7）。

Qwen2.5 Instruct 72B 每 100 万输入 token 的价格为 $0.47（优于平均水平，中位数：$0.46），每 100 万输出 token 的价格为 $0.49（非常有竞争力，中位数：$0.81）；基于提供该模型的各服务商中位数。

Qwen2.5 Instruct 72B 每 100 万输入 token 的价格为 $0.47，每 100 万输出 token 的价格为 $0.49（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 $0.39。价格可能因服务商而异。比较服务商价格

否，Qwen2.5 Instruct 72B 不是推理模型。它不进行扩展的思维链推理，而是直接作答。

Qwen2.5 Instruct 72B 支持文本输入。

Qwen2.5 Instruct 72B 支持文本输出。

否，Qwen2.5 Instruct 72B 不支持图像输入，只能处理文本。

否，Qwen2.5 Instruct 72B 不是多模态模型，仅支持文本输入。

Qwen2.5 Instruct 72B 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，Qwen2.5 Instruct 72B 是开放权重模型，其模型权重已公开，可供下载并自行托管。

Qwen2.5 Instruct 72B 有 72B 参数。

Qwen2.5 Instruct 72B 基于 Qwen License Agreement 许可证发布，允许商业使用但有限制。查看许可证

Qwen2.5 Instruct 72B 在 Artificial Analysis Intelligence Index 上的得分为 8。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 Qwen2.5 Instruct 72B。比较 API 服务商

可通过 2 家 API 服务商使用 Qwen2.5 Instruct 72B。比较服务商

Qwen2.5 Instruct 72B 智能、性能与价格分析

模型摘要

智能Updated

速度

成本

冗长度

比较摘要

技术规格

此类别中有 39 个模型

智能

速度

每任务成本

智能Updated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index

Open Weights

基准测试

Intelligence Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index

开放性指数

Artificial Analysis Openness Index: Score

Intelligence Index 比较

Intelligence Index vs. Cost per Intelligence Index Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

成本

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Cache Hit

上下文窗口

Context Window

Context Window for RAG

Context Window

模型规模（仅开放权重模型）

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

常见问题

Qwen2.5 Instruct 72B 何时发布？

谁开发了 Qwen2.5 Instruct 72B？

Qwen2.5 Instruct 72B 有多智能？

Qwen2.5 Instruct 72B 的费用是多少？

Qwen2.5 Instruct 72B API 的价格是多少？

Qwen2.5 Instruct 72B 是推理模型吗？

Qwen2.5 Instruct 72B 支持哪些输入模态？

Qwen2.5 Instruct 72B 支持哪些输出模态？

Qwen2.5 Instruct 72B 能处理图像吗？

Qwen2.5 Instruct 72B 是多模态模型吗？

Qwen2.5 Instruct 72B 的上下文窗口有多大？

Qwen2.5 Instruct 72B 是开放权重模型吗？

Qwen2.5 Instruct 72B 有多少个参数？

Qwen2.5 Instruct 72B 使用什么许可证？

Qwen2.5 Instruct 72B 在基准测试中的表现如何？

可以通过 API 使用 Qwen2.5 Instruct 72B 吗？

可以在哪里使用 Qwen2.5 Instruct 72B？