llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsQwen2.5 Coder 32B

Alibaba Cloud / Qwen Team model product

Qwen2.5 Coder 32B

Qwen2.5-Coder is a specialized coding model trained on 5.5 trillion tokens of code data, supporting 92 programming languages with a 128K context window. It excels in code generation, completion, repair, and multi-programming tasks while maintaining strong performance in mathematics and general capabilities.

Updated Aug 10, 2026. Default version: Qwen2.5-Coder 32B Instruct

Compare
LLMBoard score45.4Qwen2.5-Coder 32B Instruct
Coverage80%10 benchmark families
Context window128KTokens
Official input price$0.287Alibaba (China) 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-Coder 32B Instruct
Released
Sep 19, 2024
Knowledge cutoff
Unknown
Parameters
32B
Context window
128K
Max output
128K
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-Coder 32B Instruct category scores

Benchmark results

Published benchmark records for the scored version Qwen2.5-Coder 32B Instruct.

15 rows
Columns

Show columns

BigCodeBench-Full0.511100.0%CAug 7, 2026
BigCodeBench-Hard0.311100.0%CAug 7, 2026
MBPP0.933794.4%CAug 7, 2026
TheoremQA0.43660.0%CAug 7, 2026
HumanEval0.977692.0%CAug 7, 2026
Winogrande0.8102257.1%CAug 7, 2026
TruthfulQA0.5141823.5%CAug 7, 2026
HellaSwag0.8162742.3%CAug 7, 2026
ARC-C0.7213439.4%CAug 7, 2026
GSM8k0.9244851.1%CAug 7, 2026
MMLU-Redux0.8424812.8%CAug 7, 2026
MATH0.6517128.6%CAug 7, 2026
LiveCodeBench0.3607318.1%CAug 7, 2026
MMLU0.87710023.2%CAug 7, 2026
MMLU-Pro0.511512910.9%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

46 rows
Columns

Show columns

textcoding2451276.1873N/AAug 6, 2026
textexpert2461219.8267N/AAug 6, 2026
texthard prompts english2481271.2759N/AAug 6, 2026
text style controlcoding2501342.3873N/AAug 6, 2026
text style controlexpert2501275.2267N/AAug 6, 2026
textmath2511250.6725N/AAug 6, 2026
textindustry mathematical2531243.2619N/AAug 6, 2026
texthard prompts2541251.61,386N/AAug 6, 2026
textindustry legal and government2551256.8273N/AAug 6, 2026
text style controlmath2551269.8725N/AAug 6, 2026
text style controlindustry legal and government2561309.2273N/AAug 6, 2026
textlonger query2571251.1804N/AAug 6, 2026
text style controlhard prompts english2571319.3759N/AAug 6, 2026
textindustry business and management and financial operations2581223.6629N/AAug 6, 2026
textrussian2581227.3822N/AAug 6, 2026
text style controlrussian2581270.1822N/AAug 6, 2026
textchinese2591220.9528N/AAug 6, 2026
textindustry software and it services2591262.01,381N/AAug 6, 2026
text style controlhard prompts2601303.11,386N/AAug 6, 2026
text style controlindustry business and management and financial operations2611283.0629N/AAug 6, 2026
text style controlindustry mathematical2611268.9619N/AAug 6, 2026
text style controlindustry software and it services2631319.61,381N/AAug 6, 2026
textinstruction following2641223.22,227N/AAug 6, 2026
text style controlchinese2641279.9528N/AAug 6, 2026
text style controllonger query2681286.8804N/AAug 6, 2026
textoverall2701230.25,432N/AAug 6, 2026
textexclude ties2701126.73,370N/AAug 6, 2026
textmulti turn2701222.31,024N/AAug 6, 2026
textenglish2711248.12,652N/AAug 6, 2026
text style controlinstruction following2711264.02,227N/AAug 6, 2026
textindustry medicine and healthcare2741185.7221N/AAug 6, 2026
textnon english2761204.32,780N/AAug 6, 2026
text style controlmulti turn2771250.91,024N/AAug 6, 2026
text style controlnon english2781247.02,780N/AAug 6, 2026
text style controlexclude ties2791184.43,370N/AAug 6, 2026
textindustry life and physical and social science2801221.8956N/AAug 6, 2026
text style controloverall2801270.55,432N/AAug 6, 2026
text style controlenglish2801286.32,652N/AAug 6, 2026
text style controlindustry medicine and healthcare2821254.5221N/AAug 6, 2026
text style controlindustry life and physical and social science2851277.4956N/AAug 6, 2026
textcreative writing2891174.2836N/AAug 6, 2026
textindustry writing and literature and language2901191.01,540N/AAug 6, 2026
text style controlindustry writing and literature and language2901227.51,540N/AAug 6, 2026
text style controlcreative writing2921206.8836N/AAug 6, 2026
textindustry entertainment and sports and media2941150.7929N/AAug 6, 2026
text style controlindustry entertainment and sports and media3031187.4929N/AAug 6, 2026

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
$0.287 input, $0.861 output per 1M
Official provider
Alibaba (China)
Lowest third-party
From $0.66 input, $1 output per 1M via Cloudflare Workers AI
Tracked offerings
6
6 rows
Columns

Show columns

Nvidiaqwen/qwen2.5-coder-32b-instructglobalN/AN/A128KAug 7, 2026
Alibaba (China)qwen2-5-coder-32b-instructglobal$0.287$0.861131.1KAug 7, 2026
Cloudflare Workers AI@cf/qwen/qwen2.5-coder-32b-instructglobal$0.66$132.8KAug 7, 2026
Kilo Gatewayqwen/qwen-2.5-coder-32b-instructglobal$0.66$132.8KAug 7, 2026
OpenRouterqwen/qwen-2.5-coder-32b-instructglobal$0.66$132.8KAug 7, 2026
Cloudflare AI Gatewayworkers-ai/@cf/qwen/qwen2.5-coder-32b-instructglobal$0.66$1128KAug 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 Coder 32B 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-Coder 32B InstructSep 19, 202445.432B128K128KNoApache 2.0

What is Qwen2.5 Coder 32B?

A concise description based on the published model registry.

Qwen2.5-Coder is a specialized coding model trained on 5.5 trillion tokens of code data, supporting 92 programming languages with a 128K context window. It excels in code generation, completion, repair, and multi-programming tasks while maintaining strong performance in mathematics and general capabilities.

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 Coder 32B vs nearby models

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

Qwen2.5 Coder 32BvsPhi 4 ReasoningQwen2.5 Coder 32BvsGemma 2 27BQwen2.5 Coder 32BvsSarvam 30BQwen2.5 Coder 32BvsGemma 3 27BQwen2.5 Coder 32BvsNemotron 3 NanoQwen2.5 Coder 32BvsGranite 3.3 8B

Models similar to Qwen2.5 Coder 32B

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

#102-1.5
AC

Qwen2.5 14B

Alibaba Cloud / Qwen Team

43.9 LLMBoard

DetailsCompare
#106-2.7
AC

Qwen3 VL 235B A22B

Alibaba Cloud / Qwen Team

42.7 LLMBoard

DetailsCompare
#90+2.8
AC

Qwen3.6 35B A3B

Alibaba Cloud / Qwen Team

48.2 LLMBoard

DetailsCompare
#108-3.6
AC

Qwen3 Next 80B A3B

Alibaba Cloud / Qwen Team

41.8 LLMBoard

DetailsCompare
#86+3.6
AC

Qwen3 235B A22B

Alibaba Cloud / Qwen Team

49.0 LLMBoard

DetailsCompare
#111-5.1
AC

Qwen3 VL 30B A3B Thinking

Alibaba Cloud / Qwen Team

40.3 LLMBoard

DetailsCompare

FAQ

Common questions about Qwen2.5 Coder 32B.

When was Qwen2.5 Coder 32B released?

Qwen2.5 Coder 32B's default version was released on Sep 19, 2024.

How much does Qwen2.5 Coder 32B cost?

Qwen2.5 Coder 32B's official API price is $0.287 per million input tokens and $0.861 per million output tokens via Alibaba (China). The lowest tracked third-party offer starts at $0.66 input and $1 output via Cloudflare Workers AI.

Who created Qwen2.5 Coder 32B?

Qwen2.5 Coder 32B is published under Alibaba Cloud / Qwen Team in the model registry.

What is the context window for Qwen2.5 Coder 32B?

The default version has a 128K token context window.

Is Qwen2.5 Coder 32B open weight?

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

How many API providers offer Qwen2.5 Coder 32B?

6 published provider offerings are linked to the default version.

What models should I compare Qwen2.5 Coder 32B with?

Nearby ranked alternatives include Phi 4 Reasoning, Gemma 2 27B, Sarvam 30B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai