whatmodel.sh / Qwen3-Max-Preview

Qwen3-Max-Preview

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Qwen3-Max-Preview is a closed-weights language model from Alibaba, released September 2025.

Catalogue identity notes

Arena entry 'qwen3-max-preview' (text). Released 2025-09: Model Studio newly-released-models log: '2025-09-05 | International | qwen3-max-preview'. Separate preview model, not the official Qwen3-Max snapshot (Qwen's Qwen3-Max blog says the official release further improved the preview). Scheduled for retirement 2026-10-10.

68.7±3.2#102 of 949 LLMsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Qwen3-Max-Preview, out of 1132 with a score, then more from Alibaba.

#modelscorewhereRAMreleased
119GLM-4.7 Z.ai69±1api $1.00/M +local~58GB2025-12
120GPT-5.5 Instant OpenAI69±1comparison only2026-05
121Qwen3-Max-Preview Alibaba69±3api $2.40/M2025-09
122GPT-5.4 nano OpenAI69±1api $0.46/M2026-03
123Claude Sonnet 4.5 Anthropic69±1api $6.00/M2025-09
more from Alibaba
18Qwen3.8 Max (2.4T-A95B) Alibaba78±1api $3.00/M +local~380GB2026-08
34Qwen3.8 Max (0902) Alibaba76±1api $3.00/M2026-09
37Qwen3.8-Flash-Next Alibaba75±1local~59GB2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #73 of 466 * · 93% of its score · 1 test

Beats LongCat 2.0 (1.6T-A48B), Mistral Large 4 (public preview), Inkling Small (266B-A12B) here, though they rank higher overall. Trails Gemma 4 26B-A4B, Nemotron Cascade 2 30B-A3B, Gemma 4 31B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1434.4 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 291/379avg 1268▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%blunt
other tests1 not in a task · 2.5% of its score
testresultvs the others in its rundifficultycountswhy
Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate)96.2% ✎▁▁▂▃▄▄█▆▃▂▂▁ beats 89/140very easy · avg 94%▇ 2.5%blunt · maxed out · noisy

$ where to run it

Through an API

api · Alibaba Cloud Model Studio · $2.40/M · $1.2 in / $6 out per 1M tokens · 262k context · www.alibabacloud.com ↗ · price sourceUSD per 1M tokens, Singapore (International), qwen3-max-preview (Non-Thinking and Thinking modes), 0<Token<=32K input tier: input $1.2, output $6 (32K-128K $2.4/$12, 128K-256K $3/$15). Context-cache discount, free quota and other deployments (US/Global $0.861/$3.441 up to 32K) excluded, following the International convention of other Alibaba rows. Observed 2026-10-07.

$ how the score was worked out · LMArena leaderboard dataset 93%, Vectara hallucination leaderb… 2%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%CC BY 4.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)1▇ 2%Apache-2.0
prior · pull toward the middle▇ 5%
weighted average= 68.7

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json