Qwen 3.6 Max Preview
FrontierAlibaba (Qwen)•Released on 2026-04-20
Alibaba's most powerful Qwen model to date, released April 20, 2026. Tops multiple coding and agent benchmarks including SWE-bench Pro, Terminal-Bench 2.0, SkillsBench, QwenClawBench, QwenWebBench and SciCode. Hosted proprietary model, preview only.
87
Overall Score
Core Specs
1000K
Context Window
0K
Max Output
✓
Reasoning
✗
Open Source
Multimodal Support
textimage
Scenario Scores
User Feedback Highlights
Based on community feedback. Hover to see original reviews.
+ #1 on SWE-bench Pro (tops all Claude/GPT/DeepSeek)+ Free trial access during preview− Proprietary (not open-source)+ Leader on multiple agent benchmarks− Most benchmark #1 claims are from Alibaba− Limited independent benchmark verification+ 1M-token context window− Preview — API pricing not set
Sentiment:👍 70%😐 25%👎 5%
Pros & Cons
Pros
- +#1 on SWE-bench Pro (tops all Claude/GPT/DeepSeek)
- +Leader on multiple agent benchmarks
- +1M-token context window
- +Free trial access during preview
Cons
- −Preview — API pricing not set
- −Proprietary (not open-source)
- −Limited independent benchmark verification
- −Most benchmark #1 claims are from Alibaba
Reliability
Incidents (30d)0
View Status Page →Pricing
Input (per 1M tokens)$0.00
Output (per 1M tokens)$0.00
Free trial available
Updated on 2026-04-21
Get Started
1Visit the provider's website
2Create an account
3Start using the model
Compare with Others
Benchmarks
sweBenchPro#1 (top coding leaderboard)%
terminalBench2#1%
skillsBench#1%
qwenClawBench#1%
qwenWebBench#1%
sciCode#1%
noteRanked #1 on multiple coding and agent benchmarks per Alibaba announcement.%