How much does Qwen2.5 7B Instruct cost?

Qwen2.5 7B Instruct costs $0.04 per million input tokens and $0.10 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.000 per message.

What benchmarks has Qwen2.5 7B Instruct been tested on?

Qwen2.5 7B Instruct has been evaluated on 6 benchmarks. Top scores: IFEval: 75.8, MATH Level 5: 50.0, MMLU-PRO: 36.5.

Is Qwen2.5 7B Instruct open source?

Yes, Qwen2.5 7B Instruct is open source.

How does Qwen2.5 7B Instruct compare to Qwen3 Next 80B A3B Thinking?

Qwen2.5 7B Instruct has an average score of 57.4 while Qwen3 Next 80B A3B Thinking scores 57.5. Qwen3 Next 80B A3B Thinking slightly outperforms Qwen2.5 7B Instruct overall. Qwen2.5 7B Instruct costs $0.04/1M input vs Qwen3 Next 80B A3B Thinking at $0.10/1M input. See full comparison →

Home/Models/Qwen2.5 7B Instruct

Qwen2.5 7B Instruct

Name: Qwen2.5 7B Instruct
Price: 0.04 USD
Author: Alibaba Qwen

by Alibaba Qwen · Released Oct 2024

Open Source

57.4

avg score

Rank #79

Compare

Better than 66% of all models

Context

33K tokens (~16 books)

Input $/1M

$0.04

Output $/1M

$0.10

Type

text

License

Open Source

Benchmarks

6 tested

Data updated today

About

Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

Tested on 6 benchmarks with 35.2% average. Top scores: IFEval (75.8%), MATH Level 5 (50.0%), MMLU-PRO (36.5%).

Capabilities

reasoning

8.4

#147 globally

math

50.0

#76 globally

knowledge

21.0

#196 globally

language

75.8

#56 globally

general

34.9

#28 globally

Benchmark Scores

Compare All

Tested on 6 benchmarks · Ranked across 5 categories

Score Distribution (all 233 models)

0255075100

▲ You are here

reasoningCompare reasoning →

MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

8.4—

mathCompare math →

MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

50.0—

knowledgeCompare knowledge →

MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

36.5—

GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

5.5—

Quick compare:

vs Qwen3 Next 80B A3B Thinking

vs GPT-5.1

vs o4 Mini

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Model Family · Alibaba Qwen Qwen 2.5

Qwen2.5 72B InstructSep 2024

53.2

$0.36/M in33Kctx24 benchmarks

Qwen2.5 7B InstructOct 2024

35.2-18.0

$0.04/M in(-0.32)33Kctx6 benchmarks

Qwen2.5 Coder 32B InstructNov 2024

53.1+17.9

$0.66/M in(+0.62)33Kctx14 benchmarks

Qwen2.5 Coder 7B InstructApr 2025

44.4-8.7

$0.03/M in(-0.63)33Kctx12 benchmarks

Qwen2.5 VL 32B InstructMar 2025

$0.20/M in(+0.17)128Kctx(+95K)

Qwen2.5 VL 72B InstructFeb 2025

$0.25/M in(+0.05)32Kctx(-96K)

Qwen2.5-MaxJan 2024

41.0+41.0

N/AN/Actx8 benchmarks

See the full Qwen 2.5 family →

Similar Models

Qwen3 Next 80B A3B Thinking

Links

Info

Alibaba Qwen Pricing explorer Developers · API

Research

Documentation

Community

Source Code

BenchGecko API

qwen-2-5-7b-instruct

Specifications

Typetext
Context33K tokens (~16 books)
ReleasedOct 2024
LicenseOpen Source
StatusActive
Cost / Message~$0.000

Available On

Alibaba Qwen$0.04

Frequently Asked Questions

Qwen2.5 7B Instruct is an open-source text AI model by Alibaba Qwen, released in October 2024. It has an average benchmark score of 57.4. Context window: 33K tokens.

Benchmarks

IFEval MATH Level 5 MMLU-PRO BBH (HuggingFace)MUSR

Alibaba Qwen · Provider Alibaba Qwen · Economy All Models Compare Models Pricing Developers · API

Qwen2.5 7B Instruct

Frequently Asked Questions

Related Models

Benchmarks

Related Pages