Qwen 2.5 Coder 32B
SpecializedOpen SourceAPI Available
Benchmark Scores
79.9/100MMLU74.2
HumanEval92.7
Math68.5
Reasoning72
Coding92
About Qwen 2.5 Coder 32B
Qwen 2.5 Coder 32B is a specialized coding model that rivals GPT-4o on code generation benchmarks. It matches or exceeds much larger models on HumanEval and other coding evaluations.
Strengths
- +Excellent code generation
- +Matches GPT-4o on coding
- +Small and efficient
- +Open source
Weaknesses
- -Specialized — weaker at general tasks
- -Limited reasoning breadth
- -Narrow training focus
Pricing
Per 1M tokens
Input$0.15
Output$0.15
Quick Facts
- Context Window
- 128K
- Parameters
- 32B
- Release Date
- 2024-11-11
- Category
- Specialized
Compare Models
See how Qwen 2.5 Coder 32B stacks up against other models