CorX Labs

Qwen2.5-Coder-32B

by Alibaba Qwen · China
Open weightsTool calling131K context

For a long stretch the best open model you could run locally for code.


Specification

The numbers

Maker
Alibaba Qwen
Released
2024-11
Parameters
32B
Architecture
Dense transformer
Context window
131,072 tokens
Max output
8,192 tokens
Input
Text
Output
Text
Reasoning
No
Tool calling
Yes
Knowledge cutoff
Not reported
Licence
Apache 2.0
Availability
Not reported
Weights
Downloadable

Cost

Price per million tokens

Input
$0.070 / M tokens
Output
$0.16 / M tokens
Blended 3:1
$0.092

This model has open weights, so there is no first-party price. The figures above are a representative third-party hosting rate — you can also run it yourself for the cost of the hardware.

Published scores

Benchmarks

Figures published by Alibaba Qwen or taken from a public leaderboard. Row last checked 2026-08.

Qwen2.5-Coder-32B by capability category, with its rank among models reporting the same tests.
CategoryScore Rank
ReasoningMulti-step logic on problems that cannot be looked upNot reported
MathsCompetition mathematics, graded on the final answerNot reported
CodingLiveCodeBench, HumanEval62.0%Only model reporting these
KnowledgeBreadth of factual recall under exam conditionsNot reported
MultimodalReading charts, diagrams and photographsNot reported
Instruction followingObeying an exact, checkable formatNot reported
Human preferenceWhich answer people pick, blindNot reported

A category averages every benchmark in it that Qwen2.5-Coder-32B reports. The rank counts only models that report the same tests, so it never compares an average over three benchmarks against an average over one.

Every reported test

MMLU-ProKnowledgeNot reportedNo figure published
GPQA DiamondReasoningNot reportedNo figure published
AIME 2025MathsNot reportedNo figure published
MATH-500MathsNot reportedNo figure published
SWE-bench VerifiedCodingNot reportedNo figure published
SWE-bench ProCodingNot reportedNo figure published
Terminal-Bench 2.1CodingNot reportedNo figure published
Frontier-Bench v0.1ReasoningNot reportedNo figure published
Terminal-Bench 4.0CodingNot reportedNo figure published
LiveCodeBenchCoding31.4%Rank 11 of 11 models reporting
HumanEvalCoding92.7%Rank 3 of 46 models reporting
MMMUMultimodalNot reportedNo figure published
IFEvalInstruction followingNot reportedNo figure published
LMArena EloHuman preferenceNot reportedNo figure published

Where these numbers come from

Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.

A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.

Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.

Same maker

Other models from Alibaba Qwen

AI models with context window, price per million tokens and published benchmark scores. Sortable by any column.
Qwen3-MaxAlibaba QwenAlibaba Qwen262K$1.20$6.0085.4%92.3%69.6%Proprietary
Qwen3-Coder-480B-A35BAlibaba QwenAlibaba Qwen262K$0.30$1.2069.6%Apache 2.0
Qwen3-235B-A22BAlibaba QwenAlibaba Qwen131K$0.20$0.6068.2%71.1%85.7%Apache 2.0
Qwen3-32BAlibaba QwenAlibaba Qwen131K$0.10$0.3066.8%81.4%Apache 2.0
Qwen3-30B-A3BAlibaba QwenAlibaba Qwen131K$0.08$0.29065.8%80.4%Apache 2.0
Qwen3-14BAlibaba QwenAlibaba Qwen131K$0.06$0.2464%79.3%Apache 2.0
Qwen3-8BAlibaba QwenAlibaba Qwen131K$0.035$0.13862%76%Apache 2.0
Qwen3-4BAlibaba QwenAlibaba Qwen131K$0.02$0.0655.9%73.8%Apache 2.0
QwQ-32BAlibaba QwenAlibaba Qwen131K$0.15$0.2065.2%79.5%Apache 2.0
Qwen2.5-VL-72BAlibaba QwenAlibaba Qwen131K$0.40$0.40Qwen License
Qwen2.5-72BAlibaba QwenAlibaba Qwen131K$0.35$0.4071.1%49%Qwen License
Qwen2.5-32BAlibaba QwenAlibaba Qwen131K$0.08$0.2069%Apache 2.0
Qwen2.5-7BAlibaba QwenAlibaba Qwen131K$0.025$0.0556.3%Apache 2.0