← Models
Qwen3.6 Plus
Alibaba Cloud / Qwen Team · proprietary · qwen3.6-plus
Qwen3.6 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. It leads on Terminal-Bench 2.0 agentic coding (61.6), surpassing Claude 4.5 Opus, and achieves strong results on document understanding (OmniDocBench 91.2) and multimodal reasoning (MMMU 86.0). Compared to Qwen 3.5, it is significantly more decisive in reasoning, using fewer tokens on straightforward tasks with better agent stability.
Benchmark scores
| Benchmark | Score |
|---|---|
| CountBench | 0.98 |
| V* | 0.97 |
| HMMT 2025 | 0.97 |
| AIME 2026 | 0.95 |
| HMMT25 | 0.95 |
| MMLU-Redux | 0.94 |
| AI2D | 0.94 |
| IFEval | 0.94 |
| RefCOCO-avg | 0.94 |
| C-Eval | 0.93 |
| OmniDocBench 1.5 | 0.91 |
| GPQA | 0.90 |
| MMMLU | 0.90 |
| We-Math | 0.89 |
| MMLU-Pro | 0.89 |
| DynaMath | 0.88 |
| MathVision | 0.88 |
| MLVU | 0.87 |
| MMMU | 0.86 |
| RealWorldQA | 0.85 |
| MMMU-Pro | 0.79 |
| SWE-Bench Verified | 0.79 |
| WideSearch | 0.74 |
| MCP Atlas | 0.74 |
| SWE-bench Multilingual | 0.74 |
| TAU3-Bench | 0.71 |
| Humanity's Last Exam | 0.29 |
Pricing
- Together$0.50 / $3.00
- Novita$0.50 / $3.00
Input / output per 1M tokens
AA metrics
No Artificial Analysis link yet.
Arena Elo
- code1460
