modelbenchmark.io

Qwen2.5 Coder 32B Instruct

Alibaba · qwen-2-5-coder-32b-instruct

Compare

Qwen coding model for software agents, repository edits, and code reasoning

Specification

most-agreed values

Context
33K
Max output
29K
Released
2024-11-11
Knowledge cutoff
2024-06-30
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.66
Output
$1.00

Quality

2 benchmarks · 2 sources

Composite
4th
percentile of 334 scored models
Rank
322 / 334
±0.08 sd
Evidence
2 × 2
one source, or fewer than 3 benchmarks
Effort range
one configuration only
coding8th2/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Aider polyglot12.2default · aider diff · 2 runsAider2024-12-22
SWE-Bench verified23.5default · Skywork-SWE-32B · 2 runsSWE-bench

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo$0.66$1.0033K29K
openrouter$0.66$1.00
33K
34K
29K
34K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterInput$0.66
2026-09-06openrouterInput$0.66
2026-09-02openrouterOutput$1.00
2026-09-06openrouterOutput$1.00

Other listings of this model

same model, different key

More from Alibaba

most-hosted first