LLM Reference

Qwen2.5-Coder-32B-Instruct

Released
2024-11-12
Last refreshed
2026-05-19
Status
Researched 16d ago
CodingRAGAgentsLong contextClassificationJSON / Tool use

Qwen2.5-Coder-32B-Instruct is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 128k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Released
2024-11-12
Context
128k
Parameters
32B
Architecture
Decoder Only
Knowledge cutoff
2024-02
Specialization
code
Training
finetuned
Fine-tuning
instruct
Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website
Pricing
Output / 1M
$0.180
Input / 1M
$0.180

Cheapest of 6 routes · SiliconFlow

About

Instruction-optimized 32B code flagship for production systems requiring top-tier code reasoning, generation, and multi-file analysis.

Qwen2.5-Coder-32B-Instruct is a model in the Qwen2.5-Coder family. The structured metadata tracks a 128k-token context window, structured outputs, and code execution. This page tracks provider routes through Cloudflare Workers AI, OpenRouter, Fireworks AI, and 3 more, with the cheapest tracked route listed at $0.18 input and $0.18 output per 1M tokens. Headline tracked benchmarks include HumanEval 92.7, Aider Polyglot 16.4, and BigCodeBench 49.0.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ A

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 6

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
SiliconFlow$0.180$0.180
Serverless
Fireworks AI$0.900$0.900
Serverless
Cloudflare Workers AI$0.660$1.00
Serverless
OpenRouter$0.660$1.00
Serverless

Capabilities

Structured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
HumanEval92.72024-11https://qwenlm.github.io/blog/qwen2.5-coder-family/
Aider Polyglot16.42026-04https://aider.chat/docs/leaderboards
BigCodeBench49.02025-01 (Instruct Pass@1)https://bigcode-bench.github.io/results.json
HumanEval+87.2https://evalplus.github.io/leaderboard.html
Mostly Basic Programming Problems+79.4https://evalplus.github.io/leaderboard.html

Migration checks

No linked migration route is available for this model yet.

Rankings & picks(9)