modelbenchmark.io

Qwen3-Coder 30B-A3B Instruct

Alibaba · qwen3-coder-30b-a3b

Compare

Smaller Qwen coder for efficient local agents and repo-level fixes

Specification

most-agreed values

Context
262K
Max output
131K
Released
2025-07-31
Knowledge cutoff
2025-04
Retires
2027-03-30
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.15
Output
$0.60

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputbedrock_converse$0.075
Batch outputbedrock_converse$0.30
Priority inputbedrock_converse$0.2625
Priority outputbedrock_converse$1.05

Batch input is 50% below the interactive input price at the same listing.

Quality

1 benchmark · 1 source

Composite
56th
percentile of 344 scored models
Rank
151 / 344
±0.10 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
coding42nd1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified56.3default · EntroPO + R2E · 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 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
amazon-bedrock$0.15$0.60——262K131K—
bedrock_converse$0.15$0.60——262K16K2027-03-30
vercel$0.15$0.60——262K8K—
pinstripes · pinstripes$0.30$0.60——131K131K—

Other listings of this model

this page is one of them

The corpus files Qwen3-Coder 30B-A3B Instruct under several keys. This page is the qwen3-coder-30b-a3b listing. The full record — every host, every price and every benchmark score — is on the main Qwen3-Coder 30B-A3B Instruct page.

More from Alibaba

most-hosted first