Qwen2.5 Coder Instruct 32B
AlibabaQwenOpen WeightApache 2.0 · Commercial OK
Description
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.
Release Date
2024-11-11
Parameters
32.0B
Context Length
33K
Modalities
text
Capability Radar
23
general
30
coding
37
reasoning
30
science
35
agents
0
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 423 | 32.0 | AA |
| General Ranking | 505 | 28.0 | AA |
| Science | 565 | 21.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
75.1%SR
TruthfulQA
54.2%SR
BigCodeBench-Full
49.6%SR
BigCodeBench-Hard
27.0%SR
Language
MMLU-Redux
77.5%SR
MMLU-Pro
50.4%SR
Math
GSM8k
91.1%SR
MATH
57.2%SR
TheoremQA
43.1%SR
Reasoning
HumanEvalOpenAI (2021)
92.7%SR
MBPP
0.90 / 100SR
HellaSwagAI2 (2019)
83.0%SR
Winogrande
80.8%SR
ARC-C
70.5%SR
LiveCodeBench
31.4%SR
AA Evaluation Indices
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))76.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))63.5
Gpqa(NYU + Cohere + Anthropic (2023))41.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))29.5
Aime(MAA (Mathematical Association of America))12.0
Intelligence Index(Artificial Analysis)6.7
Hle(Center for AI Safety + Scale AI (2025))3.5
LLM Stats Category Scores
(LLM Stats (zeroeval))Language70
Math70
Reasoning70
General70
Legal60
Finance60
Healthcare60
Code60
Physics40
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
3 providers
Cheapest: Alibaba (China)Most Expensive: Kilo Gateway
ProviderInputOutput
1Alibaba (China)Cheapest
$0.287
$0.861
2OpenRouter
$0.66
$1
3Kilo Gateway
$0.66
$1
Compare pricing across different API providers for this model.