Pass IndexThe State of AISign in

Qwen3.7 Max

Qwen3.7 is a next‑generation flagship model designed for the agent‑centric era, with its core strengths lying in the breadth and depth of its agent‑level capabilities: it excels at programming, office and productivity tasks, and long‑term autonomous execution.

text → text · made by Alibaba

$2.5$7.5per Mtok in / out
Alibaba · 11 sellers

Sold by 11 ways

SellerLaneRate
Alibaba apistandard$2.5per Mtok in$7.5per Mtok outalibabacloud.com · read 2026-08-24
Novita AI aggregatorstandard$1.25per Mtok in$3.75per Mtok out$0.25per Mtok cachedapi.novita.ai · read 2026-08-25
Together AI aggregatorstandard$1.25per Mtok in$3.75per Mtok out$0.12per Mtok cacheddocs.together.ai · read 2026-08-24
ElectronHub aggregatorstandard$1.48per Mtok in$4.42per Mtok outapi.electronhub.ai · read 2026-09-16
Nous Research aggregatorstandard$1.48per Mtok in$4.42per Mtok out$0.29per Mtok cached$1.84per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12
OpenRouter aggregatorstandard$1.48per Mtok in$4.42per Mtok out$0.29per Mtok cached$1.84per Mtok cache writeopenrouter.ai · read 2026-08-24
DeepInfra aggregatorstandard$2.5per Mtok in$7.5per Mtok outapi.deepinfra.com · read 2026-08-25
Requesty aggregatoralibaba$2.5per Mtok in$7.5per Mtok out$0.25per Mtok cachedrouter.requesty.ai · read 2026-08-28
Vercel AI Gateway aggregatorstandard$2.5per Mtok in$7.5per Mtok out$0.5per Mtok cached$3.12per Mtok cache writeai-gateway.vercel.sh · read 2026-08-25
Venice AI aggregatorstandard$2.7per Mtok in$8.05per Mtok out$0.27per Mtok cached$3.35per Mtok cache writemodels.dev · read 2026-09-16
PPIO aggregatorstandard$6per Mtok in$18per Mtok outapi.ppinfra.com · read 2026-09-16

Measured 38 standings

PlaceBoardMetricScore
7thof 35Swe bench verified — Epoch AImean_score (max)77.273
12thof 42Design Arena · godotgamedev (agents)Elo1225
13thof 102Simplebench — Epoch AIScore (AVG@5) (max)0.704
15thof 80Simpleqa verified — Epoch AImean_score (max)55.767
17thof 21Ebr bench — Epoch AImean_score (max)9.524
20thof 23Gbaeval — Epoch AIOverall score (max)0.004
21stof 161Dtbench — Epoch AIAccuracy (max)92.27
23rdof 36Design Arena · htmlslides (agents)Elo1161
23rdof 127Mystery game puzzles — Epoch AImean_score (max)32
25thof 62Design Arena · webapps (agents)Elo1225
25thof 62Frontiermath tier 4 v2 — Epoch AImean_score (max)34.146
26thof 152Design Arena · dataviz (models)Elo1291
26thof 106Frontiermath tiers 1 3 v2 — Epoch AImean_score (max)64.561
27thof 43Design Arena · python-pptxslides (agents)Elo1194
27thof 123Lmca — Epoch AIScore (max)44.02
28thof 147Design Arena · 3d (models)Elo1296
28thof 109Design Arena · svg (models)Elo1244
29thof 92Design Arena · asciiart (models)Elo1231
30thof 112Ale bench — Epoch AIPerformance (max)1189.4
30thof 155Design Arena · gamedev (models)Elo1292
30thof 64Proofbench — Epoch AIAccuracy (max)26
31stof 40Design Arena · agenticgamedev (agents)Elo1161
31stof 156Design Arena · codecategories (models)Elo1291
32ndof 313GPQA Diamondmean_score (max)90.909
32ndof 290OTIS Mock AIME 2024-2025mean_score (max)95.556
33rdof 64Design Arena · fullstack (agents)Elo1201
33rdof 162Design Arena · website (models)Elo1285
34thof 402LMArena · TextScore (Elo) (max)1473
36thof 55Design Arena · androidnative (agents)Elo1170
36thof 121Webdev arena — Epoch AIArena Score (max)1516.65
38thof 150Design Arena · uicomponent (models)Elo1285
40thof 63Design Arena · mobileapps (agents)Elo1175
55thof 177Critpt — Epoch AIAccuracy (max)13.429
56thof 184Artificial Analysis · Coding IndexIndex66
67thof 143Artificial Analysis · Agentic IndexIndex23.9
69thof 168Scicode — Epoch AIScore (max)48.843
95thof 222Chess puzzles — Epoch AImean_score (max)19
165thof 656Epoch capabilities index — Epoch AIECI Score (max)153.7

About

Qwen3.7 Max — a text model from Alibaba, sold by 11 companies from $1.25 in and $3.75 out per million tokens, placed 34th of 402 on LMArena · Text.

It takes text and returns text, with a context window of 991,000 tokens. It was published in May 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning. Eleven companies sell it. The cheapest is $1.25 in and $3.75 out per million tokens at Novita AI. Beside the standard rate there is a separately routed lane. It has been measured on 38 boards, and stands best at 34th of 402 on LMArena · Text.

Every current figure

Maker
Alibaba
Register
model
Takes
text
Returns
text
Context
991,000 tokens
Longest answer
500,000 tokens
Published
May 2026
Licence
not read
Sellers
11
Price
$1.25 in and $3.75 out per million tokens — Novita AI
Boards
38
Best place
34th of 402 — LMArena · Text

Known as 4 names

qwen3.7-max-previewqwen3.7-maxQwen/Qwen3.7-Maxalibaba/qwen3.7-max