> Qwen3.6-35B-A3B is an open-weights AI model from Alibaba, released 16 Apr 2026. Index score 139 (GPT-4 = 100), rank 90 of 229 ranked models. API price $0.15 in / $1.0 out per million tokens, 262K context.

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

# Qwen3.6-35B-A3B

Alibaba

Released 16 Apr 2026

Open

[Compare](https://themodelindex.org/compare/qwen3-6-35b-a3b-vs-gpt-5-5/) [Run it yourself →](https://themodelindex.org/local/)

139128–151

Index score

#90 of 229 models

3/ 8

Core tests taken

3 of 6 areas · plus 7 anchor tests

−31

Versus the frontier at release

best then: GPT-5.4

$0.15/ $1.0

Price per million tokens

input / output, list price

262K

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 13 months earlier.

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

Show 6 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

85%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

20%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

23%

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

#90

of 219 · 139

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#61

of 207 · 18

Epoch Capabilities Index

overall capability from many benchmarks

#86

of 239 · 143.9

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

Not in the top three among current models on any category we track.

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

↗

#### API providers · 10 · per million tokens, in / out

D

Darkbloom

$0.050 / $0.70 · fp4

cheapest

A

AkashML

$0.10 / $0.90 · fp8

↗

D

DeepInfra

$0.10 / $0.95 · fp8

↗

R

Reka

$0.10 / $1.0

↗

V

Venice

$0.10 / $1.0 · fp8

↗

P

Parasail

$0.15 / $1.0 · fp8

↗

A

AtlasCloud

$0.19 / $1.11 · fp8

↗

P

Phala

$0.20 / $1.27

↗

#### Run it yourself

🤗

Official weights

Qwen/Qwen3.6-35B-A3B

↗

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

16 Apr 2026

Announcement

not linked yet

Release entry

Qwen3.6-35B-A3B (open)

Scored as

Qwen 3.6 35B-A3B

Artificial Analysis index

18

Output speed

125 tokens/s

Hugging Face

[Qwen/Qwen3.6-35B-A3B ↗](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)

## Alibaba releases · around this one

Qwen3.5

Open

16 FEB 2026

index 146

Qwen3.6-Plus

Closed

2 APR 2026

index 148

Qwen3.6-35B-A3B

Open

16 APR 2026

index 139

Qwen3.6-Max-Preview

Closed

20 APR 2026

index 153

Qwen3.7-Max

Closed

19 MAY 2026

index 162

---
Source: https://themodelindex.org/models/qwen3-6-35b-a3b/ · The Model Index · data as of 2026-10-01