Alibaba Cloud / Qwen Team model product
Qwen3.6 Plus
6 Plus is Alibaba's next-generation flagship model featuring a 1 million token native context window, up to 65,536 output tokens, and always-on chain-of-thought reasoning.
Updated Aug 12, 2026. Default version: Qwen3.6 Plus
LLMBoard score67.5Qwen3.6 Plus
Coverage100%64 benchmark families
Context window1MTokens
Official input price$0.50Alibaba API
Qwen3.6 Plus Specifications
Technical details for the model's default version.
- Version
- Qwen3.6 Plus
- Released
- Mar 31, 2026
- Knowledge cutoff
- Apr 1, 2025
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Qwen3.6 Plus Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3.6 Plus Benchmark Results
Benchmark scores for Qwen3.6 Plus.
| CC-OCR | 83.4% | 01 | 18 | 100.0% | C | |
| C-Eval | 93.3% | 01 | 18 | 100.0% | C | |
| DynaMath | 88.0% | 01 | 7 | 100.0% | C | |
| MMLongBench-Doc | 0.62 points | 01 | 5 | 100.0% | C | |
| MMMU | 86.0% | 01 | 63 | 100.0% | C | |
| MMStar | 83.3% | 01 | 22 | 100.0% | C | |
| ODinW | 51.8% | 01 | 16 | 100.0% | C | |
| RefCOCO-avg | 0.935 points | 01 | 7 | 100.0% | C | |
| TIR-Bench | 61.6% | 01 | 4 | 100.0% | C | |
| We-Math | 89.0% | 01 | 1 | 100.0% | C | |
| AI2D | 94.4% | 02 | 32 | 96.8% | C | |
| DeepPlanning | 41.5% | 02 | 9 | 87.5% | C | |
| HMMT25 | 94.6% | 02 | 25 | 95.8% | C | |
| MMLU-Pro | 88.5% | 02 | 129 | 99.2% | C | |
| SuperGPQA | 71.6% | 02 | 34 | 97.0% | C | |
| TAU3-Bench | 70.7% | 02 | 5 | 75.0% | C | |
| V* | 96.9% | 02 | 7 | 83.3% | C | |
| IFEval | 94.3% | 03 | 65 | 96.9% | C | |
| LongBench v2 | 62.0% | 03 | 17 | 87.5% | C | |
| MLVU | 86.7% | 03 | 10 | 77.8% | C | |
| MMLU-Redux | 94.5% | 03 | 48 | 95.7% | C | |
| OmniDocBench 1.5 | 91.2% | 03 | 17 | 87.5% | C | |
| PolyMATH | 77.4% | 03 | 23 | 90.9% | C | |
| AIME 2026 | 95.3% | 04 | 18 | 82.3% | C | |
| CountBench | 0.976 points | 04 | 6 | 40.0% | C | |
| Include | 85.1% | 04 | 31 | 90.0% | C | |
| MAXIFE | 88.2% | 04 | 11 | 70.0% | C | |
| MMLU-ProX | 84.7% | 04 | 32 | 90.3% | C | |
| VITA-Bench | 44.3% | 04 | 10 | 66.7% | C | |
| WideSearch | 74.3% | 04 | 9 | 62.5% | C | |
| HMMT 2025 | 96.7% | 05 | 33 | 87.5% | C | |
| MCP-Mark | 48.2% | 05 | 8 | 42.9% | C | |
| RealWorldQA | 85.4% | 05 | 26 | 84.0% | C | |
| WMT24++ | 84.3% | 05 | 23 | 81.8% | C | |
| AA-LCR | 68.3% | 06 | 16 | 66.7% | C | |
| ERQA | 65.7% | 06 | 23 | 77.3% | C | |
| Global PIQA | 89.8% | 06 | 13 | 58.3% | C | |
| MathVision | 88.0% | 06 | 32 | 83.9% | C | |
| NOVA-63 | 57.9% | 06 | 11 | 50.0% | C | |
| SkillsBench | 45.7% | 06 | 8 | 28.6% | C | |
| HMMT Feb 26 | 87.8% | 07 | 11 | 40.0% | C | |
| LiveCodeBench v6 | 87.1% | 07 | 53 | 88.5% | C | |
| SimpleVQA | 0.673 points | 07 | 13 | 50.0% | C | |
| Video-MME | 84.2% | 08 | 17 | 56.3% | C | |
| VideoMMMU | 84.0% | 10 | 26 | 64.0% | C | |
| Claw-Eval | 58.7% | 11 | 13 | 16.7% | C | |
| IMO-AnswerBench | 83.8% | 11 | 19 | 44.4% | C | |
| MMMLU | 89.5% | 11 | 49 | 79.2% | C | |
| SWE-bench Multilingual | 73.8% | 11 | 34 | 69.7% | C | |
| IFBench | 74.2% | 12 | 29 | 60.7% | C | |
| NL2Repo | 37.9% | 12 | 14 | 15.4% | C | |
| ScreenSpot Pro | 68.2% | 12 | 25 | 54.2% | C | |
| FrontierSWE | 22.0% | 15 | 15 | 0.0% | B | |
| MCP Atlas | 74.1% | 15 | 31 | 53.3% | C | |
| CharXiv-R | 81.5% | 16 | 48 | 68.1% | C | |
| Finance Agent v2 | 40.8% | 16 | 26 | 40.0% | B | |
| MMMU-Pro | 78.8% | 17 | 66 | 75.4% | C | |
| SWE-Bench Verified | 78.8% | 18 | 105 | 83.7% | C | |
| OSWorld-Verified | 62.5% | 19 | 23 | 18.2% | C | |
| Terminal-Bench 2.0 | 61.6% | 19 | 49 | 62.5% | C | |
| GPQA | 90.4% | 22 | 234 | 91.0% | C | |
| Toolathlon | 39.8% | 25 | 31 | 20.0% | C | |
| SWE-Bench Pro | 56.6% | 26 | 45 | 43.2% | C | |
| LiveBench | 70.9% | 28 | 38 | 27.0% | B | |
| Humanity's Last Exam | 28.8% | 44 | 93 | 53.3% | C |
Qwen3.6 Plus Arena Results
Preference and agent-evaluation results for the default version.
| webdev | overall | 40 | 1459.2 | 15,287 | N/A | |
| text | overall | 67 | 1436.9 | 45,498 | N/A | |
| text style control | overall | 70 | 1443.6 | 45,498 | N/A | |
| text factuality | overall | 79 | 1437.6 | 45,409 | N/A |
Qwen3.6 Plus Runtime Performance
Provider-specific output speed and catalog latency for Qwen3.6 Plus. Runtime does not affect the capability score.
| Novita | 174.652 tok/s | 1.231 s | 1M | 65.5K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3.6 Plus Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.50 input, $3 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.276 input, $1.65 output per 1M via Merge Gateway
- Tracked offerings
- 25
| Alibaba Coding Plan (China) | qwen3.6-plus | global | N/A | N/A | 1M | |
| Alibaba Coding Plan | qwen3.6-plus | global | N/A | N/A | 1M | |
| Alibaba Token Plan | qwen3.6-plus | global | N/A | N/A | 1M | |
| Alibaba Token Plan (China) | qwen3.6-plus | global | N/A | N/A | 1M | |
| Merge Gateway | qwen/qwen3.6-plus | global | $0.276 | $1.65 | 1M | |
| AIHubMix | qwen3.6-plus | global | $0.28 | $1.69 | 991K | |
| CrossModel | qwen/qwen3.6-plus | global | $0.32 | $1.88 | 1M | |
| NanoGPT | qwen-3.6-plus | global | $0.325 | $1.95 | 991.8K | |
| Pioneer | qwen3.6-plus | global | $0.325 | $1.95 | 1M | |
| Kilo Gateway | qwen/qwen3.6-plus | global | $0.325 | $1.95 | 1M | |
| OpenRouter | qwen/qwen3.6-plus | global | $0.325 | $1.95 | 1M | |
| OpenCode Go | qwen3.6-plus | global | $0.50 | $3 | 1M | |
| LLM Gateway | qwen3.6-plus | global | $0.50 | $3 | 262.1K | |
| OpenCode Zen | qwen3.6-plus | global | $0.50 | $3 | 262.1K | |
| FrogBot | qwen-3-6-plus | global | $0.50 | $3 | 1M | |
| ZenMux | qwen/qwen3.6-plus | global | $0.50 | $3 | 1M | |
| EmpirioLabs AI | qwen3-6-plus | global | $0.50 | $3 | 1M | |
| Together AI | Qwen/Qwen3.6-Plus | global | $0.50 | $3 | 1M | |
| Auriko | qwen-3.6-plus | global | $0.50 | $3 | 1M | |
| Ofox | bailian/qwen3.6-plus | global | $0.50 | $3 | 1M | |
| OrcaRouter | qwen/qwen3.6-plus | global | $0.50 | $3 | 1M | |
| Alibaba | qwen3.6-plus | global | $0.50 | $3 | 1M | |
| Vercel AI Gateway | alibaba/qwen3.6-plus | global | $0.50 | $3 | 1M | |
| Alibaba (China) | qwen3.6-plus | global | $0.50 | $3 | 1M | |
| Charm Hyper | qwen3.6-plus | global | $2 | $6 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3.6 Plus Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Qwen3.6 Plus | 67.5 | N/A | 1M | 65.5K | No | Proprietary |
What is Qwen3.6 Plus?
Key information about Qwen3.6 Plus and its available data.
6 Plus is Alibaba's next-generation flagship model featuring a 1 million token native context window, up to 65,536 output tokens, and always-on chain-of-thought reasoning. It uses a next-generation hybrid architecture optimized for efficiency and scalability. 0).
5, it is significantly more decisive in reasoning, using fewer tokens on straightforward tasks with better agent stability.
Data as of 2026-08-11.
Qwen3.6 Plus vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen3.6 Plus
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3.5 397B A17B
Alibaba Cloud / Qwen Team
AC
Qwen3.7 Plus
Alibaba Cloud / Qwen Team
AC
Qwen3.6 27B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 122B A10B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 27B
Alibaba Cloud / Qwen Team
AC
Qwen3.7 Max
Alibaba Cloud / Qwen Team
FAQ
Common questions about Qwen3.6 Plus.
When was Qwen3.6 Plus released?
Qwen3.6 Plus's default version was released on Mar 31, 2026.
How much does Qwen3.6 Plus cost?
Qwen3.6 Plus's official API price is $0.50 per million input tokens and $3 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.276 input and $1.65 output via Merge Gateway.
Who created Qwen3.6 Plus?
Qwen3.6 Plus was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3.6 Plus?
The default version has a 1M token context window.
Is Qwen3.6 Plus open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Qwen3.6 Plus?
25 provider offerings are linked to the default version.
What models should I compare Qwen3.6 Plus with?
Nearby ranked alternatives include Claude Opus 4.5, Gemini 3.5 Flash Cyber, Grok 4 Heavy.