LLMOpen weights

Qwen2.5 Coder 32B Instruct

Alibaba

Updated May 22, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: LLM
Access: Open weights
Released: November 11, 2024
License: apache_2_0
Context window: 128,000 tokens
Knowledge cutoff: June 30, 2024
Output speed: 110 tok/s
Latency (TTFT): 0.26s
Input: Text
Output: Text
API pricing: $0.66 in · $1.00 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

41.7

Coding

HumanEval	92.7
LiveCodeBench	31.4
MBPP	90.2

Math

GSM8K	91.1
MATH	57.2
MATH-500	76.7

General

MMLU	75.1
MMLU-Pro	50.4
Humanity’s Last Exam	3.8

Compare Qwen2.5 Coder 32B Instruct with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Qwen2.5 Coder 32B Instruct alternatives →