modelbenchmark.io

Qwen3.5 2B

Alibaba · qwen3-5-2b

Compare

Qwen3.5 2B is a small open-weight multimodal model from Alibaba for efficient reasoning, coding, visual understanding, tool use, and JSON output.

Specification

most-agreed values

Context
262K
Max output
33K
Released
2026-08-16
Knowledge cutoff
Retires
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.08
Output
$0.16
Cache read
$0.04

Quality

1 benchmark · 1 source

Composite
19th
percentile of 334 scored models
Rank
270 / 334
±0.24 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
reasoning21st1/4 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Chess Puzzles0.0 ±0.0defaultEpoch 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 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
qvacfreefree33K8K
requesty$0.02$0.10262K262K
nano-gpt$0.08$0.16$0.04262K33K

More from Alibaba

most-hosted first