> Qwen 3.5 Flash (hosted 35B-A3B) is a closed AI model from Alibaba, released 25 Feb 2026. Index score 140 (GPT-4 = 100), rank 88 of 229 ranked models.

[Models](https://themodelindex.org/models/) /[Alibaba](https://themodelindex.org/labs/alibaba/)

# Qwen 3.5 Flash (hosted 35B-A3B)

Alibaba

Released 25 Feb 2026

Closed

[Compare](https://themodelindex.org/compare/qwen-3-5-flash-hosted-35b-a3b-vs-kimi-k2-5/)

140128–152

Index score

#88 of 229 models

2/ 8

Core tests taken

2 of 6 areas · plus 7 anchor tests

−30

Versus the frontier at release

best then: GPT-5.3-Codex

Replaced by [Qwen 3.6 Flash](https://themodelindex.org/models/qwen-3-6-flash/)

–

Price per million tokens

no public API price found

–

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

Gemini 2.5 Pro reached this score 11 months earlier.

## Test results · by area · tick = best by any model

Show 7 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

82%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

18%

Coding

no evidence yet

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

no evidence yet

ARC-AGI-2

no result

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#88

of 219 · 140

Epoch Capabilities Index

overall capability from many benchmarks

#85

of 239 · 144.0

LMArena · Maths

maths questions in chat

#138

of 373 · 1401

LMArena · Text

overall chat quality, judged by people

#144

of 388 · 1396

LMArena · Coding

coding questions in chat

#152

of 383 · 1436

LMArena · Creative writing

creative writing

#171

of 386 · 1338

LMArena · WebDev

building web apps and front ends

#112

of 123 · 1243

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Replaced by Qwen 3.6 Flash; it no longer leads any category among current models.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

Qwen Chat

app · subscription

↗

Alibaba Cloud Model Studio

API

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

25 Feb 2026

Announcement

not linked yet

Release entry

–

Scored as

Qwen 3.5 Flash (hosted 35B-A3B)

Artificial Analysis index

–

Output speed

–

Hugging Face

closed weights

## Alibaba releases · around this one

Qwen

Closed

11 APR 2023

Tongyi Qianwen

Closed

11 APR 2023

---
Source: https://themodelindex.org/models/qwen-3-5-flash-hosted-35b-a3b/ · The Model Index · data as of 2026-10-01