llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsQwen2.5 7B

Alibaba Cloud / Qwen Team model product

Qwen2.5 7B

Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model features enhanced capabilities in mathematics, coding, and multilingual support across 29+ languages including Chinese, English, French, Spanish, and more.

Updated Aug 10, 2026. Default version: Qwen2.5 7B Instruct

Compare
LLMBoard score32.4Qwen2.5 7B Instruct
Coverage80%10 benchmark families
Context window131.1KTokens
Official input price$0.175Alibaba API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Qwen2.5 7B Instruct
Released
Sep 19, 2024
Knowledge cutoff
Unknown
Parameters
7.6B
Context window
131.1K
Max output
8.2K
Inputs
text
Outputs
text
Open weights
No
License
Apache 2.0

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Qwen2.5 7B Instruct category scores

Benchmark results

Published benchmark records for the scored version Qwen2.5 7B Instruct.

14 rows
Columns

Show columns

AlignBench0.73433.3%CAug 7, 2026
MT-Bench0.951263.6%CAug 7, 2026
MultiPL-E0.791333.3%CAug 7, 2026
MBPP0.8143763.9%CAug 7, 2026
Arena Hard0.5182632.0%CAug 7, 2026
GSM8k0.9224855.3%CAug 7, 2026
MATH0.8287161.4%CAug 7, 2026
LiveBench0.437382.7%CAug 7, 2026
HumanEval0.8427645.3%CAug 7, 2026
MMLU-Redux0.8434810.6%CAug 7, 2026
IFEval0.761656.3%CAug 7, 2026
LiveCodeBench0.3637313.9%CAug 7, 2026
MMLU-Pro0.610712917.2%CAug 7, 2026
GPQA0.42112339.5%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

No published Arena match

The default version has no published Arena rows, or its source alias has not been resolved.

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$0.175 input, $0.70 output per 1M
Official provider
Alibaba
Lowest third-party
From $0.07 input, $0.07 output per 1M via NovitaAI
Tracked offerings
4
4 rows
Columns

Show columns

NovitaAIqwen/qwen2.5-7b-instructglobal$0.07$0.0732KAug 7, 2026
Alibaba (China)qwen2-5-7b-instructglobal$0.072$0.144131.1KAug 7, 2026
OpenRouterqwen/qwen-2.5-7b-instructglobal$0.10$0.2032.8KAug 7, 2026
Alibabaqwen2-5-7b-instructglobal$0.175$0.70131.1KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Qwen2.5 7B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Qwen2.5 7B InstructSep 19, 202432.47.6B131.1K8.2KNoApache 2.0

What is Qwen2.5 7B?

A concise description based on the published model registry.

Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model features enhanced capabilities in mathematics, coding, and multilingual support across 29+ languages including Chinese, English, French, Spanish, and more.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Qwen2.5 7B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Qwen2.5 7BvsClaude Haiku 3Qwen2.5 7BvsQwen3 VL 8B ThinkingQwen2.5 7BvsQwQ 32BQwen2.5 7BvsLlama 4 ScoutQwen2.5 7BvsPhi 4 MiniQwen2.5 7BvsGemini 2.5 Flash Lite

Models similar to Qwen2.5 7B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#131+0.2
AC

QwQ 32B

Alibaba Cloud / Qwen Team

32.6 LLMBoard

DetailsCompare
#130+0.5
AC

Qwen3 VL 8B Thinking

Alibaba Cloud / Qwen Team

32.9 LLMBoard

DetailsCompare
#125+3.6
AC

Qwen3 VL 32B

Alibaba Cloud / Qwen Team

36.0 LLMBoard

DetailsCompare
#124+3.7
AC

Qwen3.5 9B

Alibaba Cloud / Qwen Team

36.1 LLMBoard

DetailsCompare
#140-4.4
AC

Qwen3.5 4B

Alibaba Cloud / Qwen Team

28.0 LLMBoard

DetailsCompare
#120+5.6
AC

Qwen2 72B

Alibaba Cloud / Qwen Team

38.0 LLMBoard

DetailsCompare

FAQ

Common questions about Qwen2.5 7B.

When was Qwen2.5 7B released?

Qwen2.5 7B's default version was released on Sep 19, 2024.

How much does Qwen2.5 7B cost?

Qwen2.5 7B's official API price is $0.175 per million input tokens and $0.70 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.07 input and $0.07 output via NovitaAI.

Who created Qwen2.5 7B?

Qwen2.5 7B is published under Alibaba Cloud / Qwen Team in the model registry.

What is the context window for Qwen2.5 7B?

The default version has a 131.1K token context window.

Is Qwen2.5 7B open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Qwen2.5 7B?

4 published provider offerings are linked to the default version.

What models should I compare Qwen2.5 7B with?

Nearby ranked alternatives include Claude Haiku 3, Qwen3 VL 8B Thinking, QwQ 32B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai