Alibaba Cloud / Qwen Team model product
Qwen3.5 35B A3B
5 35B A3B is a multimodal Mixture-of-Experts model with 35 billion total parameters and 3 billion activated parameters.
Updated Sep 8, 2026. Default version: Qwen3.5-35B-A3B
LLMBoard Score51.1Qwen3.5-35B-A3B
Coverage80%81 benchmark families
Context window262.1KTokens
Official input price$0.25Alibaba API
Qwen3.5 35B A3B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3.5 35B A3B Benchmark Results
Benchmark scores for Qwen3.5-35B-A3B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAndroidWorld_SR | Score71.10% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHypersim | Score0.13 points | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVLMsAreBlind | Score97.00% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCountBench | Score0.98 points | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkBrowseComp-zh | Score69.50% | Rank03 | Participants13 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkFullStackBench en | Score58.10% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkFullStackBench zh | Score55.00% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHallusion Bench | Score67.90% | Rank03 | Participants18 | Percentile88.24% | EvidenceC | Evaluated |
| BenchmarkMMLongBench-Doc | Score0.60 points | Rank03 | Participants5 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMMStar | Score81.90% | Rank03 | Participants25 | Percentile91.67% | EvidenceC | Evaluated |
| BenchmarkNuscene | Score14.60% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkPMC-VQA | Score62.00% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSlakeVQA | Score78.70% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkTIR-Bench | Score55.50% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkVideoMME w/o sub. | Score82.50% | Rank03 | Participants10 | Percentile77.78% | EvidenceC | Evaluated |
| BenchmarkLingoQA | Score79.20% | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMedXpertQA | Score61.40% | Rank04 | Participants12 | Percentile72.73% | EvidenceC | Evaluated |
| BenchmarkMVBench | Score74.80% | Rank04 | Participants18 | Percentile82.35% | EvidenceC | Evaluated |
| BenchmarkOCRBench | Score91.00% | Rank04 | Participants24 | Percentile86.96% | EvidenceC | Evaluated |
| BenchmarkSUNRGBD | Score0.33 points | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkZEROBench-Sub | Score0.34 points | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkDynaMath | Score85.00% | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkMMBench-V1.1 | Score91.50% | Rank05 | Participants20 | Percentile78.95% | EvidenceC | Evaluated |
| BenchmarkMMVU | Score72.30% | Rank05 | Participants5 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkOJBench | Score36.00% | Rank05 | Participants9 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkBFCL-V4 | Score67.30% | Rank06 | Participants18 | Percentile70.59% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score82.20% | Rank06 | Participants17 | Percentile68.75% | EvidenceC | Evaluated |
| BenchmarkDeepPlanning | Score22.80% | Rank06 | Participants9 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkMathVista-Mini | Score86.20% | Rank06 | Participants25 | Percentile79.17% | EvidenceC | Evaluated |
| BenchmarkRefSpatialBench | Score0.64 points | Rank06 | Participants6 | Percentile0.00% | EvidenceC | Evaluated |
Qwen3.5 35B A3B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categorychinese | Rank54 | Rating / score1,477.05 | Votes1,241 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank58 | Rating / score1,461.27 | Votes1,460 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank70 | Rating / score1,413.61 | Votes1,055 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank70 | Rating / score1,411.63 | Votes1,159 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank72 | Rating / score1,430.59 | Votes1,580 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank76 | Rating / score1,460.42 | Votes1,827 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank80 | Rating / score1,234.26 | Votes1,348 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank82 | Rating / score1,428.36 | Votes1,829 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank84 | Rating / score1,297.99 | Votes187 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank85 | Rating / score1,398.02 | Votes2,209 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank87 | Rating / score1,424.20 | Votes2,181 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank87 | Rating / score1,435.79 | Votes3,471 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank88 | Rating / score1,249.92 | Votes1,535 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank88 | Rating / score1,249.92 | Votes1,535 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank90 | Rating / score1,387.51 | Votes571 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank90 | Rating / score1,418.26 | Votes4,156 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank91 | Rating / score1,352.97 | Votes476 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank91 | Rating / score1,364.57 | Votes3,102 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank91 | Rating / score1,452.51 | Votes1,827 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank92 | Rating / score1,404.37 | Votes3,719 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts english | Rank94 | Rating / score1,438.06 | Votes6,756 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank94 | Rating / score1,415.34 | Votes9,429 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank95 | Rating / score1,412.84 | Votes847 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank95 | Rating / score1,365.57 | Votes4,083 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank95 | Rating / score1,399.92 | Votes7,595 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank96 | Rating / score1,406.95 | Votes2,605 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank96 | Rating / score1,443.35 | Votes10,452 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry writing and literature and language | Rank96 | Rating / score1,382.35 | Votes4,865 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank97 | Rating / score1,328.79 | Votes244 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank97 | Rating / score1,405.20 | Votes1,754 | ObservationsN/A | Result date |
Qwen3.5 35B A3B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.25 input, $2 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.057 input, $0.459 output per 1M via OrcaRouter
- Tracked offerings
- 17
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOrcaRouter | Provider model IDqwen/qwen3.5-35b-a3b | Regionglobal | Input / 1M$0.057 | Output / 1M$0.459 | Context262.1K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3.5-35b-a3b | Regionglobal | Input / 1M$0.057 | Output / 1M$0.459 | Context256K | Updated |
| ProviderEmpirioLabs AI | Provider model IDqwen3-5-35b-a3b | Regionglobal | Input / 1M$0.057 | Output / 1M$0.459 | Context256K | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3.5-35B-A3B | Regionglobal | Input / 1M$0.14 | Output / 1M$1 | Context262.1K | Updated |
| ProviderRequesty | Provider model IDqwen3.5-35b-a3b | Regionglobal | Input / 1M$0.14 | Output / 1M$1 | Context262.1K | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3.5-35b-a3b | Regionglobal | Input / 1M$0.1625 | Output / 1M$1.3 | Context256K | Updated |
| ProviderNanoGPT | Provider model IDqwen3.5-35b-a3b | Regionglobal | Input / 1M$0.225 | Output / 1M$1.8 | Context260.1K | Updated |
| ProviderSiliconFlow | Provider model IDQwen/Qwen3.5-35B-A3B | Regionglobal | Input / 1M$0.24 | Output / 1M$1.8 | Context262.1K | Updated |
| ProviderMixlayer | Provider model IDqwen/qwen3.5-35b-a3b | Regionglobal | Input / 1M$0.25 | Output / 1M$1.3 | Context262.1K | Updated |
| ProviderJalapeno Cloud | Provider model IDQwen3.5-35B-A3B | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context262.1K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3.5-35B-A3B | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context262.1K | Updated |
| ProviderAlibaba | Provider model IDqwen3.5-35b-a3b | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context262.1K | Updated |
| ProviderNovitaAI | Provider model IDqwen/qwen3.5-35b-a3b | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context262.1K | Updated |
| ProviderWeights & Biases | Provider model IDQwen/Qwen3.5-35B-A3B | Regionglobal | Input / 1M$0.25 | Output / 1M$1.25 | Context262.1K | Updated |
| ProviderOfox | Provider model IDbailian/qwen3.5-35b-a3b | Regionglobal | Input / 1M$0.29 | Output / 1M$1.83 | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3.5-35b-a3b | Regionglobal | Input / 1M$0.3125 | Output / 1M$1.25 | Context262.1K | Updated |
| ProviderVenice AI | Provider model IDqwen3-5-35b-a3b | Regionglobal | Input / 1M$0.3125 | Output / 1M$1.25 | Context256K | Updated |
Qwen3.5 35B A3B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3.5-35B-A3B. 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.
Qwen3.5 35B A3B Specifications
Technical details for the model's default version.
- Version
- Qwen3.5-35B-A3B
- Released
- Feb 24, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 35B
- Context window
- 262.1K
- Max output
- 65K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3.5 35B A3B 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 |
|---|
| VersionQwen3.5-35B-A3B | Released | LLMBoard51.11 | Parameters35B | Context262.1K | Max output65K | Open weightsYes | LicenseApache 2.0 |
Models similar to Qwen3.5 35B A3B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3.6 35B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 235B A22B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3.5 27B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 235B A22B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3.5 122B A10B
Alibaba Cloud / Qwen Team
AC
Qwen3.6 27B
Alibaba Cloud / Qwen Team
What is Qwen3.5 35B A3B?
Key information about Qwen3.5 35B A3B and its available data.
5-35B-A3B is a multimodal Mixture-of-Experts large language model from Alibaba Cloud / Qwen Team. It supports reasoning, coding, agentic tasks, and visual understanding, with a native 262K context window.
Data as of 2026-09-08.
FAQ
Common questions about Qwen3.5 35B A3B.
When was Qwen3.5 35B A3B released?
Qwen3.5 35B A3B's default version was released on Feb 24, 2026.
How much does Qwen3.5 35B A3B cost?
Qwen3.5 35B A3B's official API price is $0.25 per million input tokens and $2 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.057 input and $0.459 output via OrcaRouter.
Who created Qwen3.5 35B A3B?
Qwen3.5 35B A3B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3.5 35B A3B?
The default version has a 262.1K token context window.
Is Qwen3.5 35B A3B open weight?
Yes. The default version is marked as open weight under Apache 2.0.