Alibaba Cloud / Qwen Team model product
Qwen3 Max
Qwen3 Max is the flagship model in the Qwen3 series, designed for maximum performance across all tasks.
Updated Aug 12, 2026. Default version: Qwen3 Max
LLMBoard score40.7Qwen3 Max
Coverage80%6 benchmark families
Context window262.1KTokens
Official input price$1.2Alibaba API
Qwen3 Max Specifications
Technical details for the model's default version.
- Version
- Qwen3 Max
- Released
- Dec 15, 2025
- Knowledge cutoff
- Apr 1, 2025
- Parameters
- 1T
- Context window
- 262.1K
- Max output
- 65.5K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Qwen3 Max Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 Max Benchmark Results
Benchmark scores for Qwen3 Max.
| SuperGPQA | 65.1% | 10 | 34 | 72.7% | C | |
| t2-bench | 74.8% | 16 | 23 | 31.8% | C | |
| LiveCodeBench v6 | 69.0% | 32 | 53 | 40.4% | C | |
| SWE-Bench Verified | 69.6% | 62 | 105 | 41.4% | C | |
| AIME 2025 | 81.6% | 66 | 114 | 42.5% | C | |
| GPQA | 62.0% | 157 | 234 | 33.0% | C |
Qwen3 Max Arena Results
Preference and agent-evaluation results for the default version.
| text | overall | 61 | 1438.9 | 27,857 | N/A | |
| text factuality | overall | 74 | 1440.5 | 7,555 | N/A | |
| text style control | overall | 84 | 1434.4 | 27,857 | N/A | |
| text style control | overall | 103 | 1423.6 | 9,196 | N/A | |
| text | overall | 114 | 1412.7 | 9,196 | N/A |
Qwen3 Max Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 Max. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 Max Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.2 input, $6 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.359 input, $1.43 output per 1M via OrcaRouter
- Tracked offerings
- 18
| Alibaba Coding Plan (China) | qwen3-max-2026-01-23 | global | N/A | N/A | 262.1K | |
| Alibaba Coding Plan | qwen3-max-2026-01-23 | global | N/A | N/A | 262.1K | |
| iFlow | qwen3-max | global | N/A | N/A | 256K | |
| OrcaRouter | qwen/qwen3-max | global | $0.359 | $1.43 | 262.1K | |
| Merge Gateway | qwen/qwen3-max | global | $0.359 | $1.43 | 262.1K | |
| Ofox | bailian/qwen3-max | global | $0.36 | $1.43 | 262.1K | |
| Kilo Gateway | qwen/qwen3-max | global | $0.78 | $3.9 | 262.1K | |
| OpenRouter | qwen/qwen3-max | global | $0.78 | $3.9 | 262.1K | |
| LLM Gateway | qwen3-max | global | $0.845 | $3.38 | 262.1K | |
| Alibaba (China) | qwen3-max | global | $0.861 | $3.44 | 262.1K | |
| EmpirioLabs AI | qwen3-max | global | $1.08 | $5.52 | 256K | |
| Abacus | qwen3-max | global | $1.2 | $6 | 131.1K | |
| Alibaba | qwen3-max | global | $1.2 | $6 | 262.1K | |
| Vercel AI Gateway | alibaba/qwen3-max | global | $1.2 | $6 | 262.1K | |
| Deep Infra | Qwen/Qwen3-Max | global | $1.2 | $6 | 256K | |
| NanoGPT | qwen/qwen3-max | global | $1.2 | $6 | 256K | |
| NovitaAI | qwen/qwen3-max | global | $2.11 | $8.45 | 262.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3 Max Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Qwen3 Max | 40.7 | 1T | 262.1K | 65.5K | No | Proprietary |
What is Qwen3 Max?
Key information about Qwen3 Max and its available data.
Qwen3 Max is the flagship model in the Qwen3 series, designed for maximum performance across all tasks. It excels in reasoning, mathematics, coding, and complex problem-solving while maintaining strong multilingual capabilities. Optimized for production use cases requiring the highest quality outputs.
Data as of 2026-08-11.
Qwen3 Max vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen3 Max
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 Next 80B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 32B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3.5 9B
Alibaba Cloud / Qwen Team
AC
Qwen3 235B A22B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 235B A22B
Alibaba Cloud / Qwen Team
AC
Qwen3 Next 80B A3B
Alibaba Cloud / Qwen Team
FAQ
Common questions about Qwen3 Max.
When was Qwen3 Max released?
Qwen3 Max's default version was released on Dec 15, 2025.
How much does Qwen3 Max cost?
Qwen3 Max's official API price is $1.2 per million input tokens and $6 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.359 input and $1.43 output via OrcaRouter.
Who created Qwen3 Max?
Qwen3 Max was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 Max?
The default version has a 262.1K token context window.
Is Qwen3 Max open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Qwen3 Max?
18 provider offerings are linked to the default version.
What models should I compare Qwen3 Max with?
Nearby ranked alternatives include Qwen3.5 9B, Qwen3 Next 80B A3B Thinking, Grok 4.3.