DataLearner logo
QW

Qwen 3.6 Plus Preview

Chat model

Qwen 3.6 Plus Preview

Release date: 2026-03-31Updated: 2026-04-02 15:49:26.9122,805
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
1M
Chinese support
Supported
Reasoning ability

Qwen 3.6 Plus Preview is an AI model published by Alibaba, released on 2026-03-31, for Chat model, and 1M context length, under the 不开源 license, with a 95.30 score on AIME 2026.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen 3.6 Plus Preview

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Mode (Default)Standard Mode
Context length
1M tokens
Max output length
64K tokens
Model type
Chat model
Modality (in / out)
No data
Release date
2026-03-31
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Qwen 3.6 Plus Preview

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Qwen 3.6 Plus Preview

Official resources

DataLearnerAI blog
No blog post yet
Qwen 3.6 Plus Preview

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.500/ 1M$3.00/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text5m$0.625/ 1M$0.050/ 1M
Qwen 3.6 Plus Preview

Benchmark Results

Qwen 3.6 Plus Preview currently shows benchmark results led by MMLU Pro (5 / 126, score 88.50), LiveCodeBench (10 / 120, score 87.10), GPQA Diamond (18 / 180, score 90.40). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

6 evaluations
Benchmark / mode
Score
Rank/total
C-Eval
Thinking Mode
93.30
2 / 9
GPQA Diamond
Thinking Mode
90.40
18 / 180
MMLU Pro
Thinking Mode
88.50
5 / 126
LiveBench
Standard Mode
70.85
34 / 115
HLE
Thinking Mode
28.80
85 / 164
HLE
Thinking ModeTools
50.60
21 / 164

Coding and Software Engineer

5 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Thinking Mode
87.10
10 / 120
SWE-bench Verified
Thinking ModeTools
78.80
20 / 109
73.80
8 / 21
56.60
17 / 47
SWE-Bench Pro - Public
Thinking ModeTools
56.60
17 / 47

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Thinking Mode
74.20
6 / 29

AI Agent - Tool Usage

2 evaluations
Benchmark / mode
Score
Rank/total
Terminal Bench 2.0
Thinking ModeTools
61.60
16 / 46
Tool Decathlon
Thinking ModeTools
39.80
6 / 9

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
AIME 2026
Thinking Mode
95.30
3 / 15
IMO-AnswerBench
Thinking Mode
83.80
12 / 21

Long Context

2 evaluations
Benchmark / mode
Score
Rank/total
AA-LCR
Thinking Mode
68.30
7 / 14
LongBench v2
Standard Mode
62
3 / 11

Compare with other models

Qwen 3.6 Plus Preview

Publisher

Qwen 3.6 Plus Preview

Model Overview

Qwen 3.6 Plus Preview is an AI model published by Alibaba, released on 2026-03-31, for Chat model, and 1M context length, under the 不开源 license, with a 95.30 score on AIME 2026.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code