The Model Index
Models/Alibaba

Qwen3-Max

AlibabaClosed weightsFlagship

Qwen3-Max is a closed AI model from Alibaba with an index score of 135 (GPT-4 = 100), rank 117 of 217.

135119–151Index score#117 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
5 Sep 2025ReleasedReplaced by Qwen3.6-Max-Preview

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100Qwen3-Max

o1 reached this score 9 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
73%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
19%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
no result
Agentsevidence
APEX-Agents
no result
Professional workevidence
Finance Agent (v2)
no result
Novel problemsno evidence yet
ARC-AGI-2
no result
Long tasksno evidence yet
METR time horizon
no result

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on each leaderboard

The Model Indexthird-party tests, our method#117of 217 · 135

Best attop three among current models

Replaced by Qwen3.6-Max-Preview; it no longer leads any category among current models.

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released5 Sep 2025
Announcementnot linked yet
Release entryQwen3-Max (preview; official 09-24)
Scored asQwen3-Max
Output speed–
Hugging Faceclosed weights

Alibaba releasesaround this one

This page as a chartDownload PNG