> Qwen3.8-Max is a closed AI model from Alibaba, released 3 Aug 2026. Index score 170 (GPT-4 = 100), rank 20 of 229 ranked models.

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

# Qwen3.8-Max

Alibaba

Released 3 Aug 2026

Closed

Flagship

[Compare](https://themodelindex.org/compare/qwen3-8-max-vs-kimi-k3/) [Announcement](https://qwenlm.github.io/qwen-code-docs/en/blog/cases/qwencode-bailian-skill-openai-cover-gen/)

170158–181

Index score

#20 of 229 models

2/ 8

Core tests taken

2 of 6 areas · plus 10 anchor tests

−17

Versus the frontier at release

best then: Claude Opus 5

–

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_

GPT-5.3-Codex reached this score 6 months earlier.

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

Show 10 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

93%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

75%

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

#20

of 219 · 170

LMArena · Vision

understanding images

#2

of 149 · 1301

LMArena · Maths

maths questions in chat

#17

of 373 · 1497

LMArena · Creative writing

creative writing

#19

of 386 · 1468

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#11

of 207 · 45

LMArena · Text

overall chat quality, judged by people

#23

of 388 · 1481

LMArena · Coding

coding questions in chat

#28

of 383 · 1522

LMArena · WebDev

building web apps and front ends

#9

of 123 · 1671 · early

Epoch Capabilities Index

overall capability from many benchmarks

#20

of 239 · 156.6

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

1st

understanding images

LMArena · Vision

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 · 1 · per million tokens, in / out

A

Alibaba

$2.0 / $6.0

cheapest

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

3 Aug 2026

Announcement

[qwenlm.github.io ↗](https://qwenlm.github.io/qwen-code-docs/en/blog/cases/qwencode-bailian-skill-openai-cover-gen/)

Release entry

Qwen3.8-Max (preview 07-19; weights 08-12)

Scored as

Qwen 3.8 Max

Artificial Analysis index

45 · 0902

Weights

[huggingface.co/Qwen/Qwen3.8-2.4T-A95B) ↗](https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B))

Output speed

39 tokens/s

Hugging Face

closed weights

## Alibaba releases · around this one

Qwen3.7-Max

Closed

19 MAY 2026

index 162

Qwen3.7-Plus

Closed

1 JUN 2026

index 147

Qwen3.8-Max

Closed

3 AUG 2026

index 170

Qwen3.8-2.4T-A95B

Open

12 AUG 2026

~169 est.

Qwen3.8-27B

Open

14 AUG 2026

index 152

---
Source: https://themodelindex.org/models/qwen3-8-max/ · The Model Index · data as of 2026-10-01