Alibaba Cloud / Qwen Team model product
Qwen3.8 Max
4 trillion total parameters, 95 billion active parameters, and a 262,144-token native context window.
Updated Sep 8, 2026. Default version: Qwen3.8 Max
LLMBoard Score86.9Qwen3.8 Max
Coverage40%33 benchmark families
Context window1MTokens
Official input price$2Alibaba API
Qwen3.8 Max Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3.8 Max Benchmark Results
Benchmark scores for Qwen3.8 Max.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAndroidBench | Score75.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAndroidWorld | Score85.30% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCoWorkBench | Score74.80% | Rank01 | Participants6 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkERQA | Score77.80% | Rank01 | Participants26 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench | Score60.20% | Rank01 | Participants9 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score82.80% | Rank01 | Participants39 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLongBench v2 | Score66.30% | Rank01 | Participants17 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMobileWorld | Score77.80% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score86.10% | Rank01 | Participants24 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPaperBench | Score93.00% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPerceptionBench | Score63.50% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPLawBench | Score73.20% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPRBench-Finance | Score58.30% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPRBench-Legal | Score57.60% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkQwenQoderBench | Score58.40% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkQwenReactBench | Score1,724.00 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkQwenSVG | Score1,713.00 points | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkQwenSWEBench | Score80.70% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSkillsBench | Score70.20% | Rank01 | Participants9 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVideoMME w sub. | Score90.40% | Rank01 | Participants10 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVision2Web | Score69.00% | Rank01 | Participants5 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWorkspace Bench | Score67.70% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMLS-Bench Lite | Score41.00% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkWideSearch | Score81.90% | Rank02 | Participants11 | Percentile90.00% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score52.40% | Rank03 | Participants16 | Percentile86.67% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools, text-only) | Score56.20% | Rank03 | Participants5 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkLVBench | Score81.80% | Rank03 | Participants28 | Percentile92.59% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score92.90% | Rank03 | Participants24 | Percentile91.30% | EvidenceC | Evaluated |
| BenchmarkRealWorldQA | Score88.00% | Rank03 | Participants31 | Percentile93.33% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,299.71 rating | Rank03 | Participants107 | Percentile98.11% | EvidenceA | Evaluated |
Qwen3.8 Max Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categoryocr | Rank02 | Rating / score1,314.73 | Votes5,092 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank03 | Rating / score1,471.41 | Votes309 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank03 | Rating / score1,516.49 | Votes1,872 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank03 | Rating / score1,299.71 | Votes7,244 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank03 | Rating / score1,618.44 | Votes1,869 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank04 | Rating / score1,518.80 | Votes2,045 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank04 | Rating / score1,509.56 | Votes873 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank04 | Rating / score1,511.67 | Votes371 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank04 | Rating / score1,516.57 | Votes873 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank04 | Rating / score1,496.28 | Votes371 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank04 | Rating / score1,295.05 | Votes2,403 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank04 | Rating / score1,334.05 | Votes630 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank04 | Rating / score1,686.07 | Votes1,868 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank04 | Rating / score1,686.07 | Votes1,868 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank04 | Rating / score1,702.44 | Votes1,326 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank05 | Rating / score1,326.63 | Votes1,837 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank05 | Rating / score1,311.56 | Votes2,403 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank05 | Rating / score1,321.94 | Votes5,092 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank05 | Rating / score1,312.86 | Votes7,244 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank05 | Rating / score1,326.40 | Votes1,837 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank05 | Rating / score1,657.16 | Votes184 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank06 | Rating / score1,485.88 | Votes2,602 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank06 | Rating / score1,515.76 | Votes3,547 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank06 | Rating / score1,520.73 | Votes2,045 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank06 | Rating / score1,336.40 | Votes630 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank07 | Rating / score1,536.69 | Votes863 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank07 | Rating / score1,500.94 | Votes488 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank07 | Rating / score1,488.41 | Votes2,412 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank07 | Rating / score1,465.07 | Votes309 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank07 | Rating / score1,318.54 | Votes459 | ObservationsN/A | Result date |
Qwen3.8 Max Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2 input, $6 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $1.6 input, $4.8 output per 1M via Vancine
- Tracked offerings
- 31
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAlibaba Token Plan | Provider model IDqwen3.8-max | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderKenari | Provider model IDqwen3-8-max | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderSCNet Token Plan | Provider model IDQwen3.8-Max | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAlibaba Token Plan (China) | Provider model IDqwen3.8-max | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderVancine | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$1.6 | Output / 1M$4.8 | Context1M | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3.8-Max | Regionglobal | Input / 1M$1.65 | Output / 1M$4.95 | Context256K | Updated |
| ProviderAIHubMix | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$1.69 | Output / 1M$5.07 | Context991K | Updated |
| ProviderAlibaba (China) | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$1.78 | Output / 1M$5.33 | Context1M | Updated |
| ProviderSCX.ai | Provider model IDQwen3.8-Max | Regionglobal | Input / 1M$1.82 | Output / 1M$5.45 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$1.82 | Output / 1M$5.45 | Context1M | Updated |
| ProviderCrossModel | Provider model IDqwen/qwen3.8-max | Regionglobal | Input / 1M$1.88 | Output / 1M$5.63 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDqwen/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context991K | Updated |
| ProviderOpenCode Go | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDalibaba/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDalibaba/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderDigitalOcean | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderAlibaba | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderOfox | Provider model IDbailian/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderRequesty | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderCharm Hyper | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderModal | Provider model IDQwen/Qwen3.8-2.4T-A95B | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderClinePass | Provider model IDcline-pass/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDqwen3-8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderEden AI | Provider model IDqwen/qwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderFireworks AI | Provider model IDaccounts/fireworks/models/qwen3p8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderAbacus | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| Providerabove.dev | Provider model IDqwen3.8-max | Regionglobal | Input / 1M$2.2 | Output / 1M$6.6 | Context1M | Updated |
Qwen3.8 Max Runtime Performance
Provider-specific output speed and catalog latency for Qwen3.8 Max. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepInfra | Output Speed60.87 tok/s | Catalog Latency8.02 s | Max Input256K | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3.8 Max Specifications
Technical details for the model's default version.
- Version
- Qwen3.8 Max
- Released
- Aug 2, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 2.4T
- Context window
- 1M
- Max output
- 131.1K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- Qwen3.8-Max License
Qwen3.8 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 |
|---|
| VersionQwen3.8 Max | Released | LLMBoard86.93 | Parameters2.4T | Context1M | Max output131.1K | Open weightsYes | LicenseQwen3.8-Max License |
Models similar to Qwen3.8 Max
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3.8 Flash Next
Alibaba Cloud / Qwen Team
AC
Qwen3.8 Flash
Alibaba Cloud / Qwen Team
AC
Qwen3.7 Max
Alibaba Cloud / Qwen Team
AC
Qwen3.8 27B
Alibaba Cloud / Qwen Team
AC
Qwen3.7 Plus
Alibaba Cloud / Qwen Team
AC
Qwen3.6 Plus
Alibaba Cloud / Qwen Team
What is Qwen3.8 Max?
Key information about Qwen3.8 Max and its available data.
4T-A95B open-weight checkpoint, is a mixture-of-experts model from Alibaba Cloud / Qwen Team with always-on thinking and a context window extensible to about 1 million tokens. 8 Max API family with text and image input.
Data as of 2026-09-08.
FAQ
Common questions about Qwen3.8 Max.
When was Qwen3.8 Max released?
Qwen3.8 Max's default version was released on Aug 2, 2026.
How much does Qwen3.8 Max cost?
Qwen3.8 Max's official API price is $2 per million input tokens and $6 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $1.6 input and $4.8 output via Vancine.
Who created Qwen3.8 Max?
Qwen3.8 Max was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3.8 Max?
The default version has a 1M token context window.
Is Qwen3.8 Max open weight?
Yes. The default version is marked as open weight under Qwen3.8-Max License.
How many API providers offer Qwen3.8 Max?
31 provider offerings are linked to the default version.