modelbenchmark.io

Qwen3.8 27B

Alibaba · qwen-3-8-27b

Compare

Dense 27B vision-language model for coding, agent tasks, and image and video understanding

Specification

most-agreed values

Context
66K
Max output
33K
Released
2026-08-14
Knowledge cutoff
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.99
Output
$1.49
Cache read
$0.25

Quality

1 benchmark · 1 source

Composite
63rd
percentile of 334 scored models
Rank
126 / 334
±0.53 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
general48th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
LiveBench75.8default · 23 runsLiveBench2026-06-25

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

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
neuralwatt$0.45$3.20$0.25262K66K
venice$0.45$3.20262K66K
cerebras$0.99$1.4966K33K

Price history

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

DateHostField$/M
2026-09-07cerebrasInput$0.99
2026-09-13cerebrasInput$0.99
2026-09-07cerebrasOutput$1.49
2026-09-13cerebrasOutput$1.49

Other listings of this model

this page is one of them

The corpus files Qwen3.8 27B under several keys. This page is the qwen-3-8-27b listing. The full record — every host, every price and every benchmark score — is on the main Qwen3.8 27B page.

More from Alibaba

most-hosted first