Alibaba Cloud / Qwen Team model product
Qwen3 Max
Qwen3 Max is an LLM from Alibaba Cloud / Qwen Team and the flagship model in the Qwen3 series, with capabilities in reasoning, mathematics, coding, complex problem-solving, and multilingual use.
Updated Sep 8, 2026. Default version: Qwen3 Max
LLMBoard Score42.3Qwen3 Max
Coverage0%6 benchmark families
Context window256KTokens
Official input price$1.2Alibaba API
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.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSuperGPQA | Score65.10% | Rank10 | Participants34 | Percentile72.73% | EvidenceC | Evaluated |
| Benchmarkt2-bench | Score74.80% | Rank16 | Participants23 | Percentile31.82% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score69.00% | Rank40 | Participants62 | Percentile36.07% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,439.01 rating | Rank51 | Participants210 | Percentile76.08% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,440.61 rating | Rank61 | Participants121 | Percentile50.00% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score69.60% | Rank66 | Participants113 | Percentile41.96% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score81.60% | Rank69 | Participants119 | Percentile42.37% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,434.62 rating | Rank70 | Participants210 | Percentile66.99% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score62.00% | Rank169 | Participants247 | Percentile31.71% | EvidenceC | Evaluated |
Qwen3 Max Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categorygerman | Rank21 | Rating / score1,464.74 | Votes595 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank22 | Rating / score1,463.27 | Votes838 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank27 | Rating / score1,468.28 | Votes1,454 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank27 | Rating / score1,485.38 | Votes527 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank32 | Rating / score1,467.95 | Votes611 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank41 | Rating / score1,436.90 | Votes5,106 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank42 | Rating / score1,440.59 | Votes1,450 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank42 | Rating / score1,454.81 | Votes763 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank43 | Rating / score1,457.44 | Votes4,193 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank44 | Rating / score1,451.93 | Votes838 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank47 | Rating / score1,459.60 | Votes1,291 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank47 | Rating / score1,448.43 | Votes1,484 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank47 | Rating / score1,483.72 | Votes1,469 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank47 | Rating / score1,450.17 | Votes595 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank48 | Rating / score1,397.12 | Votes703 | ObservationsN/A | Result date |
| Arenatext | Categorymulti turn | Rank48 | Rating / score1,446.32 | Votes4,521 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank48 | Rating / score1,429.42 | Votes15,708 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank49 | Rating / score1,435.89 | Votes19,317 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank49 | Rating / score1,473.81 | Votes1,454 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank50 | Rating / score1,400.36 | Votes435 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank51 | Rating / score1,479.20 | Votes2,092 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank51 | Rating / score1,448.42 | Votes13,464 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank51 | Rating / score1,439.01 | Votes27,194 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank52 | Rating / score1,446.12 | Votes1,306 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank53 | Rating / score1,432.14 | Votes3,697 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank54 | Rating / score1,455.32 | Votes1,019 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank55 | Rating / score1,451.60 | Votes431 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank55 | Rating / score1,438.57 | Votes6,099 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank57 | Rating / score1,456.51 | Votes5,309 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank57 | Rating / score1,420.52 | Votes7,241 | ObservationsN/A | Result date |
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
- 22
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProvideriFlow | Provider model IDqwen3-max | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context256K | Updated |
| ProviderAlibaba Coding Plan (China) | Provider model IDqwen3-max-2026-01-23 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderAlibaba Coding Plan | Provider model IDqwen3-max-2026-01-23 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderOrcaRouter | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$0.359 | Output / 1M$1.43 | Context262.1K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$0.359 | Output / 1M$1.43 | Context262.1K | Updated |
| ProviderOfox | Provider model IDbailian/qwen3-max | Regionglobal | Input / 1M$0.36 | Output / 1M$1.43 | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$0.78 | Output / 1M$3.9 | Context262.1K | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$0.78 | Output / 1M$3.9 | Context262.1K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3-max | Regionglobal | Input / 1M$0.845 | Output / 1M$3.38 | Context262.1K | Updated |
| ProviderAlibaba (China) | Provider model IDqwen3-max | Regionglobal | Input / 1M$0.861 | Output / 1M$3.44 | Context262.1K | Updated |
| ProviderEmpirioLabs AI | Provider model IDqwen3-max | Regionglobal | Input / 1M$1.08 | Output / 1M$5.52 | Context256K | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3-Max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context256K | Updated |
| ProviderLLM Gateway | Provider model IDalibaba/qwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context256K | Updated |
| ProviderLLMTR | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context256K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDalibaba/qwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderAlibaba | Provider model IDqwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderEden AI | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderAbacus | Provider model IDqwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context131.1K | Updated |
| ProviderNanoGPT | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$1.2 | Output / 1M$6 | Context256K | Updated |
| ProviderNovitaAI | Provider model IDqwen/qwen3-max | Regionglobal | Input / 1M$2.11 | Output / 1M$8.45 | Context262.1K | Updated |
Qwen3 Max Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 Max. Runtime does not affect the capability score.
No runtime data
No 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 Specifications
Technical details for the model's default version.
- Version
- Qwen3 Max
- Released
- Dec 15, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 1T
- Context window
- 256K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Qwen3 Max Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen3 Max | Released | LLMBoard42.27 | Parameters1T | Context256K | Max output131.1K | Open weightsNo | LicenseProprietary |
Models similar to Qwen3 Max
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 VL 235B A22B
Alibaba Cloud / Qwen Team
AC
Qwen3 235B A22B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 9B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 235B A22B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 Next 80B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 32B Thinking
Alibaba Cloud / Qwen Team
What is Qwen3 Max?
Key information about Qwen3 Max and its available data.
Qwen3 Max is an LLM from Alibaba Cloud / Qwen Team and the flagship model in the Qwen3 series. It is designed for reasoning, mathematics, coding, complex problem-solving, multilingual use, and production applications requiring high-quality outputs.
Data as of 2026-09-08.
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 256K 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?
22 provider offerings are linked to the default version.