modelbenchmark.io

qwen3-4b

Alibaba · qwen3-4b

Compare

Specification

most-agreed values

Context
33K
Max output
33K
Released
—
Knowledge cutoff
—
Retires
—
Open weights
—
Input
—
Output
—

Price

US dollars per million tokens · most-agreed

Input
$0.08
Output
$0.24

Quality

1 benchmark · 1 source

Composite
26th
percentile of 344 scored models
Rank
254 / 344
±0.11 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
reasoning27th1/4 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
GPQA diamond48.0 ±2.7default · 2 runsEpoch AI2026-08-28

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
nebius$0.08$0.24——33K33K—
fireworks_ai$0.20$0.20——41K41K—

More from Alibaba

most-hosted first