Qwen3.6 Plus

Apr 2026
Qwen3.6 Plus
Compare in
on
—per task?
$0.50 / $3per 1M in / out
56 tok/sfirst token in 2.1 s?
1Mcontext

Rankingin thinking mode?

Strong at

S
Tool calling#9 of 242
A
Science#50 of 312Long context#61 of 273Knowledge#64 of 318Instructions#26 of 245
B
Agents & work tasks#81 of 175Reasoning#94 of 334Vision#35 of 124

Alternatives?

ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen+72%-52%$0.13Pass back reasoning_content+3BetterGPT-6 Lunamedium+11%-82%$0.017Function calling only with none · Chat Completions+3CheaperDeepSeek V4.1 Flash 1017maxOpen+67%-53%$0.26Pass back reasoning_content · Chat Completions+4CheaperClaude Haiku 5.5max+61%-82%$0.21Remove sampling parameters+5CheaperMiniMax M3.1 Flashthinking+58%-77%$0.22Complete model response must be appended

History

10 versions
2525.52626.527Apr 26Release dateAA Intelligence Index 4.3.23.6 Plus3.7 Plus
2525.52626.527Apr 26Release dateAA Intelligence Index 4.3.23.6 Plus

Benchmarks

all categories
Chat & Knowledge
Humanity's Last Exam27.8#94
AA Omniscience Index0.9#64
CritPt (physics)2.9#96
AA Intelligence Index 4.3.2≈27#67
AA Omniscience · Accuracy26.4#100
AA Omniscience · Hallucination Rate34.6#49
AA-LCR (long context) 1.178.3#61
GPQA Diamond88.2#50
Coding
Terminal-Bench Hard (version unstated)43.9#22
SWE-bench Pro (edition unstated)lab56.6
Terminal-Bench 2.161.4#51
Agents & Tool Use
GDPval-AA (work tasks) 2.124.5#81
τ³-Banking · AA20.8#53
τ²-bench · AA97.7#9
Writing & Language
IFBench (instructions)75.2#26
Vision & Documents
MMMU-Pro (vision)78#35

FAQ

How much does Qwen3.6 Plus cost?›

$0.50 per 1M input tokens and $3 per 1M output tokens; cheapest via lab-qwen at $0.28 / $1.65.

Is Qwen3.6 Plus free to use?›

There is no free API; the cheapest paid price is $0.28 per 1M input tokens.

How good is Qwen3.6 Plus, and what is it best at?›

#94 of 334 in Chat & Knowledge, #52 of 97 in Coding, #81 of 175 in Agents & Tool Use, #59 of 195 in Writing & Language, #35 of 124 in Vision & Documents. Strongest at: Tool calling, Science, Long context, Knowledge, Instructions.

Is Qwen3.6 Plus better than Grok Build 0.1?›

On AA Intelligence Index 4.3.2, Qwen3.6 Plus scores 27 vs 27.2 — about the same.

How can I use Qwen3.6 Plus?›

Through the API of Alibaba.

What is the context window of Qwen3.6 Plus?›

1M tokens, with up to 66K output tokens.

When was Qwen3.6 Plus released? Is there a newer version?›

Released 2026-04-02. It has been superseded by Qwen3.7 Plus.

Is Qwen3.6 Plus open source?›

No, Qwen3.6 Plus is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.

Can Qwen3.6 Plus read images?›

It accepts text and images, video as input.

What is Qwen3.6 Plus?›

Qwen3.6 Plus is a closed language model from Alibaba (Qwen), released Apr 2026.

What are the best alternatives to Qwen3.6 Plus?›

MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).