> Qwen3 is an open-weights AI model from Alibaba, released 29 Apr 2025. Index score 131 (GPT-4 = 100), rank 116 of 229 ranked models.

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

# Qwen3

Alibaba

Released 29 Apr 2025

Open

Date verified

[Compare](https://themodelindex.org/compare/qwen3-vs-o3-2025-04/) [Announcement](https://qwenlm.github.io/blog/qwen3/)

131119–142

Index score

#116 of 229 models

1/ 8

Core tests taken

1 of 6 areas · plus 8 anchor tests

−16

Versus the frontier at release

best then: o3

–

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_

o1 reached this score 5 months earlier.

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

Show 6 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

71%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

evidence

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

#116

of 219 · 131

LMArena · Text

overall chat quality, judged by people

#92

of 388 · 1434

LMArena · Maths

maths questions in chat

#91

of 373 · 1434

LMArena · Coding

coding questions in chat

#96

of 383 · 1480

LMArena · Creative writing

creative writing

#105

of 386 · 1394

Epoch Capabilities Index

overall capability from many benchmarks

#87

of 239 · 143.8

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 · 2 · per million tokens, in / out

D

DeepInfra

$0.12 / $0.50 · fp8

cheapest

A

Alibaba

$0.13 / $0.52

↗

#### Run it yourself

🤗

Official weights

Qwen/Qwen3-30B-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

29 Apr 2025

Announcement

[qwenlm.github.io ↗](https://qwenlm.github.io/blog/qwen3/)

Release entry

Qwen3

Scored as

Qwen3-235B-A22B

Artificial Analysis index

–

Output speed

–

Hugging Face

not linked

## Alibaba releases · around this one

Qwen2.5-Max

Closed

28 JAN 2025

index 116

QwQ-32B

Open

6 MAR 2025

index 127

Qwen3

Open

29 APR 2025

index 131

Qwen3-Coder

Open

22 JUL 2025

Qwen3-Max

Closed

5 SEP 2025

index 137

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