modelbenchmark.io

Qwen3-30B-A3B

Alibaba · qwen-3-30b

Compare

Qwen instruction model for multilingual chat, reasoning, and tool use

Specification

most-agreed values

Context
41K
Max output
16K
Released
2025-04-28
Knowledge cutoff
2025-04
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.12
Output
$0.50

Quality

3 benchmarks · 1 source

Composite
36th
percentile of 334 scored models
Rank
215 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning33rd2/4 bench
math42nd1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202544.2 ±5.2default · 2 runsEpoch AI2026-08-30
GPQA diamond56.0 ±2.8default · 2 runsEpoch AI2026-08-30
Chess Puzzles2.5 ±1.0default · 2 runsEpoch AI2026-08-30

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
vercel_ai_gateway · vercel-ai-gateway$0.10$0.3041K16K
vercel$0.12$0.5041K16K

Other listings of this model

this page is one of them

The corpus files Qwen3-30B-A3B under several keys. This page is the qwen-3-30b listing. The full record — every host, every price and every benchmark score — is on the main Qwen3-30B-A3B page.

More from Alibaba

most-hosted first