whatmodel.sh / Qwen2.5 Coder 32B Instruct

Qwen2.5 Coder 32B Instruct

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Qwen2.5 Coder 32B Instruct is an open-weights language model from Alibaba, released November 2024. Its published size is 32.8B parameters and a 131k-token context window. Licence: apache-2.0.

56.6±0.7#239 of 719 LLMsfrom 25 benchmark results across 11 sources

$ how it compares

The LLMs ranked either side of Qwen2.5 Coder 32B Instruct, out of 828 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
284Llama 4 Maverick (402B-A17B) Meta57±1api $0.42/M +local~65GB2025-04
285Claude 3.5 Sonnet (2024-06-20) Anthropic57±1comparison only2024-06
286Qwen2.5 Coder 32B Instruct Alibaba57±1api $0.74/M +local~21GB2024-11
287Qwen3 4B Thinking 2507 Alibaba57±1local~3.9GB2025-08
288Gemini 1.5 Pro Experimental (0827) Google56±1comparison only2024-08
more from Alibaba
18Qwen3.8 Max (2.4T-A95B) Alibaba78±1api $3.00/M +local~380GB2026-08
34Qwen3.8 Max (0902) Alibaba76±1api $3.00/M2026-09
37Qwen3.8-Flash-Next Alibaba75±1local~59GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #184 of 458 · 88% of its score · 17 tests

Beats Gemini 2.5 Flash, Qwen3.5 4B, Qwen3 30B-A3B Instruct 2507 here, though they rank higher overall. Trails QwQ-32B-Preview, OpenThinker 32B, Command A Reasoning (08-2025) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval +192.1% ✎▁·▁▁▃▄▆▅█▃▃▁ beats 97/99easy · avg 79%▇▇▇▇▇▇▇▇ 19%sharp · several runs
HumanEval+ +187.2% ✎▁·▁▁▁▃▄▄▄█▃▃ beats 97/99easy · avg 74%▇▇▇▇▇▇▇ 18%sharp · several runs
LiveCodeBench official (Jan 1–Nov 1, 2024)41.6% ✎▁▁·▁▂▄▆█▅▂·▂ beats 25/31hard · avg 26%▇▇▇▇▇ 12%sharp · at its level
Aider polyglot (225 exercises, two attempts)16.4% ✎▂·▂▃▅▂▃█▆▄▂▂ beats 7/49very hard · avg 8.5%▇▇▇▇ 10%sharp
Aider code editing (133 Exercism Python exercises, two attempts)71.4% ✎▁·▁▂▄▁▆▄█▆▂▂ beats 51/62medium · avg 54%▇▇▇ 7.0%at its level
MBPP+ +177.0% ✎▁···▁▁▂▅▇█▆▃ beats 73/75easy · avg 68%▇▇ 5.9%several runs
Luau Leetcode fully solved (Torpedo Software)24.5% ✎▁▁▁▃·▁▂▃▅▃█▇ beats 5/49hard · avg 18%▇ 3.3%at its level
WebApp1K-Duo-React pass@1 (onekq-ai)41.6% ✎▁··▁·▁▃▁▆█▇█ beats 4/45hard · avg 32%▇ 2.3%at its level
9 more tests
testresultvs the others in its rundifficultycountswhy
MBPP lab90.2% ✎█···███·██·█ beats 6/6easy · avg 78%▇ 2.3%typical
MultiPL-E lab79.4% ✎▄·▄····▄▄·▄█ beats 5/6easy · avg 71%▇ 2.1%typical
WebApp1K-React pass@1 (onekq-ai)66.8% ✎▃▁▁█▁▄▅▃▄▇▁▄ beats 16/31medium · avg 44%▇ 1.8%sharp · at its level · noisy
CodeReviewQA: change localisation (hard), invariant accuracy64.3% ✎█▂▁▁▂▂▂▃▅▅▅▇ beats 43/47medium · avg 36%▇ 1.5%sharp · at its level · noisy
CRUXEval-I lab75.2% ✎█·██·█··█·██ beats 6/6medium · avg 57%▇ 1.1%at its level
CodeReviewQA: automated code refinement, exact match rate44.1% ✎▁▁▁▁▁▁▂▂▃█▅▄ beats 41/47hard · avg 33%▇ 1.0%at its level
CodeReviewQA: solution identification (hard), invariant accuracy85.7% ✎▃··▁▂▂▃▂█▃▄▃ beats 45/47medium · avg 54%▇ 1.0%sharp · at its level · noisy
CRUXEval-O lab83.4% ✎▄·█··▄·▄··▄▄ beats 6/6medium · avg 55%▇ 0.4%blunt · at its level
CodeReviewQA: change type recognition, invariant accuracy79.1% ✎▁▁▁······▁▃█ beats 46/47easy · avg 67%▇ 0.0%blunt · at its level · noisy
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #253 of 393 * · 4.3% of its score · 1 test

Beats Mistral Small 4 (119B-A6.5B), Ministral 3 14B Reasoning 2512 here, though they rank higher overall. Trails Flan-T5 XXL, Granite 4.0 H 1B, Granite 4.0 1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1270.6 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 103/379avg 1268▇▇ 4.3%blunt
other tests4 not in a task · 7.6% of its score
testresultvs the others in its rundifficultycountswhy
DSEffi-Bench Pass (1,000 data-science tasks, greedy)34.1% ✎▅··▃▅·█·▃██▃ beats 4/15hard · avg 24%▇ 2.8%at its level
RobloxQA v2.0 multiple choice (Torpedo Software)84.6% ✎▁▁▃▁█▄▃▃▆▂▂▂ beats 5/49easy · avg 78%▇ 2.4%typical
BigCodeBench (Instruct) lab49.6% ✎▄······▄▄█·█ beats 6/6medium · avg 38%▇ 1.6%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)74.7% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 222/276medium · avg 73%▇ 0.8%at its level · noisy

$ where to run it

Through an API

api · Cloudflare · $0.74/M · $0.66 in / $1 out per 1M tokens · 131k context · developers.cloudflare.com ↗ · price sourceWorkers AI published marginal USD per 1M tokens after free allocation. Workers plan fees excluded; billed in Neurons. Published USD rates are rounded. Product: Workers AI. API model: @cf/qwen/qwen2.5-coder-32b-instruct. Settings: plan=Workers Paid, free allocation=excluded, billing=published marginal USD rates; service bills Neurons. Currency: USD.

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Qwen2.5 Coder 32B Instruct · needs ~19.9 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Qwen2.5 Coder 32B Instruct · needs ~19.9 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/Qwen2.5-Coder-32B-Instruct-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Qwen2.5 Coder 32B Instruct · needs ~20.18 GB · from ollama.com
    chat in the terminal
    ollama run qwen2.5-coder:32b

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Qwen2.5 Coder 32B Instruct · needs ~18.4 GB, Mac only · from huggingface.co/lmstudio-community
    chat in the terminal
    mlx_lm.chat --model lmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lmstudio-community/Qwen2.5-Coder-32B-Instruct-MLX-4bit

Official weights and documentation: huggingface.co/Qwen ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 34%, Qwen (Alibaba) vendor-reporte… 16%, LiveCodeBench official websit… 12% and 8 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
EvalPlus / EvalPerf published evaluation runs3▇▇▇▇▇▇▇▇▇▇ 34%Apache-2.0
Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card) · lab-reported8▇▇▇▇▇ 16%Factual vendor-reported score (not licensed content)
LiveCodeBench official website results (2024-12-26)1▇▇▇▇ 12%CC-BY-SA-4.0
Aider polyglot benchmark runs1▇▇▇ 10%Apache-2.0
Aider code editing benchmark runs (old edit leaderboard)1▇▇ 7%Apache-2.0
Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode2▇▇ 6%MIT
LMArena leaderboard dataset1▇ 4%CC BY 4.0
WebApp1K models leaderboard (onekq-ai)2▇ 4%MIT
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (arXiv:2503.16167v2)4▇ 4%CC-BY-4.0
DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation — authors' own model runs1▇ 3%CC BY 4.0
Open Portuguese LLM Leaderboard (archived)1▇ 1%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 56.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json