Qwen3.6 Max Preview
Qwen · released Apr 27, 2026
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...
Specification
- Context window
- 262K
- Max output
- 66K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- No
Intelligence
41.1
89th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
47 t/s
Median across providers
Latency
1.33s
Time to first token
Cost per task
$0.54
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)95.9%
- GPQA Diamond88.8%
- IFBench76.6%
- AA-LCR (long context)72.0%
- SciCode46.9%
- Terminal-Bench Hard43.9%
- Humanity's Last Exam30.8%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 95.9% |
| GPQA Diamond | 88.8% |
| IFBench | 76.6% |
| AA-LCR (long context) | 72.0% |
| SciCode | 46.9% |
| Terminal-Bench Hard | 43.9% |
| Humanity's Last Exam | 30.8% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GPT-5.6 TerraOpenAI42.1
- GLM 5.3 FlashZ.ai41.8
- Claude Opus 4.8Anthropic41.8
- Nex-N2-ProNex AGI41.7
- Qwen3.6 Max PreviewQwen41.1
- Ling 3.1 FlashInclusionAI41.1
- Gemini 3.8 FlashGoogle40.9
- Claude Opus 4.7Anthropic40.7
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GPT-5.6 Terra | 42.1 |
| GLM 5.3 Flash | 41.8 |
| Claude Opus 4.8 | 41.8 |
| Nex-N2-Pro | 41.7 |
| Qwen3.6 Max Preview | 41.1 |
| Ling 3.1 Flash | 41.1 |
| Gemini 3.8 Flash | 40.9 |
| Claude Opus 4.7 | 40.7 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $1.03
- Output / 1M tokens
- $6.16
- Cached input / 1M
- Not offered
- Blended 3:1
- $2.31
One task, estimated
$0.54
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.