Models / Qwen/ Qwen3.6 Plus

Qwen3.6 Plus

Qwen · released Apr 2, 2026

Input: text, images and video. Output: text.InputOutput
Type
Proprietary
Input
None held
Output
None held
Cached
None held

We don't hold a list price for this model yet · hosted only — we hold no downloadable copy

Our take

Written Aug 3, 2026

Qwen 3.6 Plus is a hosted-only multimodal model from Alibaba that handles up to one million tokens in a single request and accepts text, images and video. It excels at coding and following complex instructions, though creative writing is a clear weak spot and all tracked providers charge the same premium rate.

Who should pick it

Choose this for long-document analysis at one million tokens, coding tasks where it scores highest among its own measured skills, or hard-prompt following where it is second only to its coding score. It also suits multimodal workflows that need video or image input sent to text output. Skip it if you need a permissive licence or local deployment, if creative writing quality matters, or if you want price competition between providers.

The case for it

  • Strongest measured capability is coding, with an Arena Coding score 87.8 points above its own creative-writing score and 51.1 points above its overall text score.
  • One-million-token request limit, exceptional for long-document work.
  • Consistent hard-prompt performance, the second-highest score in its own measured profile.

The case against it

  • Creative writing is a clear relative weakness, scoring 87.8 points below its own coding mark and 36.7 points below its overall text score — the lowest of all seven measured Arena categories.
  • Premium pricing with no budget alternative: all three tracked offers charge identically, so there is no price competition even across its own providers.
  • Throughput varies significantly across Alibaba endpoints, with a 29 percent spread between the two measured speeds and no disclosed reason.
00

How good is it?

IntelligencePuzzles, maths, exam questions

3 of 5

Arena Text (overall)41st of 143 · 1443.6

Arena Hard Prompts 39th of 143Arena Maths 29th of 139LiveBench Data Analysis 25th of 35LiveBench Mathematics 28th of 35LiveBench Reasoning 29th of 35

CodingWriting and fixing code on its own

3.5 of 5

Arena Coding42nd of 143 · 1494.7

Arena Code (WebDev) 28th of 74LiveBench Coding 16th of 35

AgenticPlanning, calling tools, staying on task

Scored, not ratedLiveBench Agentic Coding · 30th of 35 · 41.4

Qwen3.6 Plus is not on Arena Agent (IPS), which is where the rating would come from, so there is no rating here. It is on LiveBench Agentic Coding, in 30th of 35 with 41.4.

WritingWe do not rate this

Scored, not ratedThe placings are on the right.

Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Qwen3.6 Plus placed and give it no mark out of five.

Arena Creative Writing 44th of 143 · 1406.9LiveBench Language 23rd of 35 · 75
Also scored, on boards we give no mark for
Arena Instruction Following 40th of 143LiveBench 27th of 35LiveBench Instruction Following 32nd of 35

These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.

Every published score for this model15 scoresEvery figure we hold, from 15 boards, with who ran it and a link to the source — including the boards no rating above is built on.
LiveBenchreasoning
68.9independentsource ↗
78.2independentsource ↗
69.9independentsource ↗
75.8independentsource ↗
1494.7independentsource ↗
1467.3independentsource ↗
1455.2independentsource ↗
1443.6independentsource ↗
1457.9independentsource ↗
01

Or rent it from someone else

Cheapest published offer

Cheapest of 3 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.

per 1M tokens
$0.33 in / $1.95 out
Context served
1M
Throughput
Not measured
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$0.33 / $1.951Mnot measuredUnknownUnknownUnknown
Alibaba Cloudfp8$0.33 / $1.951M34 tok/sNoYesunknown periodUnknown
Alibaba Cloud$0.33 / $1.951M53 tok/sNoYesunknown periodUnknown

Across the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.

What each host's API supports

From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.

Supported
Not supported
Not published
host gave no parameter list
API features per host
ProviderTool callingJSON outputStrict schema
OpenRouter
Alibaba Cloudfp8
Alibaba Cloud

Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.

02

Models people weigh against Qwen3.6 Plus

03

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 1494.7 on Arena Codingleaderboard
Aug 2, 2026BenchmarkScored 1406.9 on Arena Creative Writingleaderboard
Aug 2, 2026BenchmarkScored 1467.3 on Arena Hard Promptsleaderboard
Aug 2, 2026BenchmarkScored 1436.5 on Arena Instruction Followingleaderboard
Aug 2, 2026BenchmarkScored 1455.2 on Arena Mathsleaderboard
Aug 2, 2026BenchmarkScored 1443.6 on Arena Text (overall)leaderboard
Aug 2, 2026BenchmarkScored 1457.9 on Arena Code (WebDev)leaderboard
Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Jun 25, 2026BenchmarkScored 68.9 on LiveBenchleaderboard
Jun 25, 2026BenchmarkScored 41.4 on LiveBench Agentic Codingleaderboard

Prices last checked 9d ago

What we do not know about this model yet

  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • 1 of 3 listings do not say whether they train on prompts.
  • We don't hold a list price for this model yet — the gap is ours, not the lab's.
  • We hold no cached-input rate for any of its listings.
04

Licence and identifiers

What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.

Licence

Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.

Identifiers

Modality record
text+image+video->text
Catalogue slug
qwen-qwen3-6-plus

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us