Pass IndexThe State of AISign in

Qwen3.6 Plus

The Qwen3.6 native vision-language Plus series models demonstrate exceptional performance on par with the current state-of-the-art models, with a significant improvement in overall results compared to the 3.5 series.

text + image + file → text · made by Alibaba

$0.33→$1.95per Mtok in / out
AtlasCloud · 7 sellers

Sold by 8 ways

SellerLaneRate
AtlasCloud aggregatorstandard$0.33per Mtok in$1.95per Mtok out$0.033per Mtok cachedapi.atlascloud.ai · read 2026-09-20
Nous Research aggregatorstandard$0.33per Mtok in$1.95per Mtok out$0.41per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12
OpenRouter aggregatorstandard$0.33per Mtok in$1.95per Mtok out$0.41per Mtok cache writeopenrouter.ai · read 2026-08-24
Requesty aggregatoralibaba$0.5per Mtok in$3per Mtok out$0.05per Mtok cachedrouter.requesty.ai · read 2026-08-28
Together AI aggregatorstandard$0.5per Mtok in$3per Mtok outmodels.dev · read 2026-10-31
Vercel AI Gateway aggregatorstandard$0.5per Mtok in$3per Mtok out$0.05per Mtok cached$0.62per Mtok cache writeai-gateway.vercel.sh · read 2026-08-25
ElectronHub aggregatorstandard$1per Mtok in$4per Mtok outapi.electronhub.ai · read 2026-10-31
PPIO 0 ways$8per Mtok in$48per Mtok out
PPIO aggregatornot on the seller's list todaystandard$8per Mtok in$48per Mtok outapi.ppinfra.com · read 2026-10-08

Measured 28 standings

PlaceBoardMetricScore
8thof 23Cl bench — Epoch AIOverall0.203
27thof 72Frontiermath tier 4 — Epoch AImean_score8.333
32ndof 101FrontierMath (Tiers 1-3)mean_score26.207
32ndof 35Swe bench verified — Epoch AImean_score57.851
32ndof 71Vending bench 2 — Epoch AIScore5114.872
43rdof 93Simpleqa verified — Epoch AImean_score44.144
64thof 326GPQA Diamondmean_score88.384
64thof 306OTIS Mock AIME 2024-2025mean_score93.333
66thof 114Design Arena · svg (models)Elo1159
66thof 122Frontiermath tiers 1 3 v2 — Epoch AImean_score38.246
68thof 141LMArena · WebDevScore (Elo)1461
69thof 154Design Arena · dataviz (models)Elo1228
69thof 135Webdev arena — Epoch AIArena Score1460.53
70thof 150Design Arena · 3d (models)Elo1199
70thof 163Design Arena · codecategories (models)Elo1234
70thof 169Design Arena · website (models)Elo1242
71stof 162Design Arena · gamedev (models)Elo1211
72ndof 163Artificial Analysis · Coding IndexIndex54.5
74thof 157Design Arena · uicomponent (models)Elo1226
81stof 93Design Arena · asciiart (models)Elo1112
88thof 414LMArena · TextScore (Elo)1443
94thof 132Ale bench — Epoch AIPerformance670.15
109thof 142Mystery game puzzles — Epoch AImean_score (none)12
117thof 154Chess puzzles — Epoch AImean_score14
126thof 235Dtbench — Epoch AIAccuracy81.87
133rdof 197Lmca — Epoch AIScore33.09
156thof 260Critpt — Epoch AIAccuracy2.857
174thof 235Scicode — Epoch AIScore40.741

About

Qwen3.6 Plus — a text model from Alibaba, sold by 7 companies from $0.33 in and $1.95 out per million tokens, placed 64th of 326 on GPQA Diamond.

It takes text, images and files and returns text, with a context window of 1,000,000 tokens. It was published in August 2025, trained on material up to April 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under ocr, reasoning, code and agents. Seven companies sell it. The cheapest is $0.33 in and $1.95 out per million tokens at AtlasCloud. Beside the standard rate there is a separately routed lane. It has been measured on 28 boards, and stands best at 64th of 326 on GPQA Diamond.

Every current figure

Maker
Alibaba
Register
model
Takes
text + image + file
Returns
text
Context
1,000,000 tokens
Longest answer
500,000 tokens
Published
August 2025
Knowledge to
April 2025
Licence
not read
Sellers
7
Maker's own price
not read
Price
$0.33 in and $1.95 out per million tokens — AtlasCloud
Boards
28
Best place
64th of 326 — GPQA Diamond

Known as 3 names

Qwen 3.6 Plusqwen/qwen3.6-plusalibaba/qwen3.6-plus