Qwen2.5-Coder 32B Instruct logo

Qwen2.5-Coder 32B Instruct

Qwen

Qwen2.5-Coder is a powerful coding model, expertly trained on 5.5 trillion tokens across 92 programming languages. With an extensive 128K context window, it's designed for superior code generation, completion, and repair. Beyond excelling at diverse programming tasks, Qwen2.5-Coder also demonstrates impressive mathematical and general knowledge.

Model Specifications

Technical details and capabilities of Qwen2.5-Coder 32B Instruct

Core Specifications

32.0B Parameters

Model size and complexity

5500.0B Training Tokens

Amount of data used in training

128.0K / 128.0K

Input / Output tokens

February 29, 2024

Knowledge cutoff date

September 18, 2024

Release date

Capabilities & License

Multimodal Support
Not Supported
Web Hydrated
No
License
Apache-2.0

Resources

Research Paper
https://arxiv.org/abs/2409.12186
API Reference
https://www.alibabacloud.com/help/en/model-studio/developer-reference/use-qwen-by-calling-api
Code Repository
https://github.com/QwenLM/Qwen2.5-Coder

Performance Insights

Check out how Qwen2.5-Coder 32B Instruct handles various AI tasks through comprehensive benchmark results.

100
75
50
25
0
92.7
HumanEval
92.7
(93%)
91.1
GSM8K
91.1
(91%)
90.2
MBPP
90.2
(90%)
83
HellaSwag
83
(83%)
80.8
WinoGrande
80.8
(81%)
77.5
MMLU-Redux
77.5
(78%)
75.1
MMLU
75.1
(75%)
70.5
ARC-Challenge
70.5
(71%)
57.2
MATH
57.2
(57%)
54.2
TruthfulQA
54.2
(54%)
50.4
MMLU-Pro
50.4
(50%)
49.6
BigCodeBench-Full
49.6
(50%)
43.1
TheoremQA
43.1
(43%)
31.4
LiveCodeBench
31.4
(31%)
27
BigCodeBench-Hard
27
(27%)
HumanEval
GSM8K
MBPP
HellaSwag
WinoGrande
MMLU-Redux
MMLU
ARC-Challenge
MATH
TruthfulQA
MMLU-Pro
BigCodeBench-Full
TheoremQA
LiveCodeBench
BigCodeBench-Hard

Model Comparison

See how Qwen2.5-Coder 32B Instruct stacks up against other leading models across key performance metrics.

100
80
60
40
20
0
92.7
HumanEval - Qwen2.5-Coder 32B Instruct
92.7
(93%)
88.4
HumanEval - Qwen2.5-Coder 7B Instruct
88.4
(88%)
84.8
HumanEval - Qwen2.5 7B Instruct
84.8
(85%)
86.6
HumanEval - Qwen2.5 72B Instruct
86.6
(87%)
87.8
HumanEval - Gemma 3 27B
87.8
(88%)
90.2
MBPP - Qwen2.5-Coder 32B Instruct
90.2
(90%)
83.5
MBPP - Qwen2.5-Coder 7B Instruct
83.5
(84%)
79.2
MBPP - Qwen2.5 7B Instruct
79.2
(79%)
88.2
MBPP - Qwen2.5 72B Instruct
88.2
(88%)
74.4
MBPP - Gemma 3 27B
74.4
(74%)
31.4
LiveCodeBench - Qwen2.5-Coder 32B Instruct
31.4
(31%)
18.2
LiveCodeBench - Qwen2.5-Coder 7B Instruct
18.2
(18%)
28.7
LiveCodeBench - Qwen2.5 7B Instruct
28.7
(29%)
55.5
LiveCodeBench - Qwen2.5 72B Instruct
55.5
(56%)
39
LiveCodeBench - Gemma 3 27B
39
(39%)
57.2
MATH - Qwen2.5-Coder 32B Instruct
57.2
(57%)
46.6
MATH - Qwen2.5-Coder 7B Instruct
46.6
(47%)
75.5
MATH - Qwen2.5 7B Instruct
75.5
(76%)
83.1
MATH - Qwen2.5 72B Instruct
83.1
(83%)
89
MATH - Gemma 3 27B
89
(89%)
91.1
GSM8K - Qwen2.5-Coder 32B Instruct
91.1
(91%)
83.9
GSM8K - Qwen2.5-Coder 7B Instruct
83.9
(84%)
91.6
GSM8K - Qwen2.5 7B Instruct
91.6
(92%)
95.8
GSM8K - Qwen2.5 72B Instruct
95.8
(96%)
95.9
GSM8K - Gemma 3 27B
95.9
(96%)
HumanEval
MBPP
LiveCodeBench
MATH
GSM8K
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 7B Instruct
Qwen2.5 7B Instruct
Qwen2.5 72B Instruct
Gemma 3 27B

Detailed Benchmarks

Dive deeper into Qwen2.5-Coder 32B Instruct's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Math

GSM8K

o1
97.1%
Nova Micro
92.3%
Claude 3 Sonnet
Claude 3 Sonnet
92.3%
Qwen2.5 7B Instruct
Qwen2.5 7B Instruct
91.6%
Llama 3.1 Nemotron 70B Instruct
Llama 3.1 Nemotron 70B Instruct
91.4%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
91.1%
Qwen2 72B Instruct
Qwen2 72B Instruct
91.1%
Gemini 1.5 Pro
Gemini 1.5 Pro
90.8%
Grok-1.5
Grok-1.5
90.0%
Gemma 2 9B
Gemma 2 9B
68.6%
Current model
Other models
Avg (89.6%)

Coding

HumanEval

Claude 3.5 Sonnet
Claude 3.5 Sonnet
93.7%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
92.7%
o1-mini
92.4%
Claude 3.5 Sonnet
Claude 3.5 Sonnet
92.0%
Mistral Large 2
Mistral Large 2
92.0%
GPT-4o
90.2%
Nova Pro
89.0%
DeepSeek-V2.5
DeepSeek-V2.5
89.0%
Current model
Other models
Avg (91.4%)

MBPP

Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
90.2%
Qwen2.5 72B Instruct
Qwen2.5 72B Instruct
88.2%
Qwen2.5 32B Instruct
Qwen2.5 32B Instruct
84.0%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
83.5%
Qwen2.5 14B Instruct
Qwen2.5 14B Instruct
82.0%
Phi-3.5-MoE-instruct
80.8%
Qwen2 72B Instruct
Qwen2 72B Instruct
80.2%
Qwen2.5 7B Instruct
Qwen2.5 7B Instruct
79.2%
Current model
Other models
Avg (83.5%)

LiveCodeBench

Grok-3 Mini
Grok-3 Mini
80.0%
DeepSeek-V3
DeepSeek-V3
40.5%
Gemma 3 27B
Gemma 3 27B
39.0%
DeepSeek-V3
DeepSeek-V3
37.6%
Gemini 2.0 Flash
Gemini 2.0 Flash
35.1%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
31.4%
Qwen2.5 7B Instruct
Qwen2.5 7B Instruct
28.7%
Qwen2 7B Instruct
Qwen2 7B Instruct
26.6%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
18.2%
Current model
Other models
Avg (37.5%)

Reasoning

HellaSwag

Claude 3 Opus
Claude 3 Opus
95.4%
Claude 3 Haiku
Claude 3 Haiku
85.9%
Qwen2.5 32B Instruct
Qwen2.5 32B Instruct
85.2%
Phi-3.5-MoE-instruct
83.8%
Mistral NeMo Instruct
Mistral NeMo Instruct
83.5%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
83.0%
Gemma 2 9B
Gemma 2 9B
81.9%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
76.8%
Llama 3.2 3B Instruct
Llama 3.2 3B Instruct
69.8%
Phi-3.5-mini-instruct
69.4%
Current model
Other models
Avg (81.5%)

Knowledge

MATH

o3-mini
97.9%
Claude 3 Opus
Claude 3 Opus
60.1%
Qwen2 72B Instruct
Qwen2 72B Instruct
59.7%
Phi-3.5-MoE-instruct
59.5%
Gemini 1.5 Flash 8B
Gemini 1.5 Flash 8B
58.7%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
57.2%
Ministral 8B Instruct
Ministral 8B Instruct
54.5%
Llama 3.2 11B Instruct
Llama 3.2 11B Instruct
51.9%
Grok-1.5
Grok-1.5
50.6%
Gemini 1.0 Pro
Gemini 1.0 Pro
32.6%
Current model
Other models
Avg (58.3%)

MMLU

o1
91.8%
Gemma 3 27B
Gemma 3 27B
76.9%
Command R+
75.7%
Claude 3 Haiku
Claude 3 Haiku
75.2%
Gemma 2 27B
Gemma 2 27B
75.2%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
75.1%
Olmo 2 32B
Olmo 2 32B
74.9%
Llama 3.2 11B Instruct
Llama 3.2 11B Instruct
73.0%
Gemini 1.0 Pro
Gemini 1.0 Pro
71.8%
Llama 3.2 3B Instruct
Llama 3.2 3B Instruct
63.4%
Current model
Other models
Avg (75.3%)

Hallucination

TruthfulQA

Phi-3.5-MoE-instruct
77.5%
Qwen2.5 14B Instruct
Qwen2.5 14B Instruct
58.4%
Jamba 1.5 Large
58.3%
Qwen2.5 32B Instruct
Qwen2.5 32B Instruct
57.8%
Qwen2 72B Instruct
Qwen2 72B Instruct
54.8%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
54.2%
Jamba 1.5 Mini
54.1%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
50.6%
Mistral NeMo Instruct
Mistral NeMo Instruct
50.3%
Current model
Other models
Avg (57.3%)

Non categorized

ARC-Challenge

Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
70.5%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
60.9%
Current model
Other models
Avg (65.7%)

WinoGrande

Gemma 2 27B
Gemma 2 27B
83.7%
Phi-3.5-MoE-instruct
81.3%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
80.8%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
72.9%
Phi-3.5-mini-instruct
68.5%
Current model
Other models
Avg (77.4%)

MMLU-Pro

DeepSeek-R1
DeepSeek-R1
84.0%
Qwen2.5 7B Instruct
Qwen2.5 7B Instruct
56.3%
Phi-3.5-MoE-instruct
54.3%
Jamba 1.5 Large
53.5%
Grok-1.5
Grok-1.5
51.0%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
50.4%
Llama 3.1 8B Instruct
Llama 3.1 8B Instruct
48.3%
Phi-3.5-mini-instruct
47.4%
Qwen2 7B Instruct
Qwen2 7B Instruct
44.1%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
40.1%
Current model
Other models
Avg (52.9%)

MMLU-Redux

DeepSeek-R1
DeepSeek-R1
92.9%
DeepSeek-V3
DeepSeek-V3
89.1%
Qwen2.5 72B Instruct
Qwen2.5 72B Instruct
86.8%
Qwen2.5 32B Instruct
Qwen2.5 32B Instruct
83.9%
Qwen2.5 14B Instruct
Qwen2.5 14B Instruct
80.0%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
77.5%
Qwen2.5 7B Instruct
Qwen2.5 7B Instruct
75.4%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
66.6%
Current model
Other models
Avg (81.5%)

TheoremQA

Qwen2.5 32B Instruct
Qwen2.5 32B Instruct
44.1%
Qwen2.5-Coder 32B Instruct
Qwen2.5-Coder 32B Instruct
43.1%
Qwen2.5 14B Instruct
Qwen2.5 14B Instruct
43.0%
Qwen2.5-Coder 7B Instruct
Qwen2.5-Coder 7B Instruct
34.0%
Current model
Other models
Avg (41.1%)

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for Qwen2.5-Coder 32B Instruct. Compare costs across platforms to find the best pricing for your use case.

OpenAI
Anthropic
Google
Mistral AI
Cohere

Share your feedback

Hi, I'm Charlie Palars, the founder of Deepranking.ai. I'm always looking for ways to improve the site and make it more useful for you. You can write me through this form or directly through X at @palarsio.

Your feedback helps us improve our service

Stay Ahead with AI Updates

Get insights on Gemini Pro 2.5, Sonnet 3.7 and more top AI models