Alibaba Cloud / Qwen Team model product
Qwen3.8 27B
78-billion-parameter multimodal foundation model for coding, professional work, research, and long-horizon agents.
Updated Sep 8, 2026. Default version: Qwen3.8-27B
LLMBoard Score74.9Qwen3.8-27B
Coverage40%23 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable
Qwen3.8 27B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3.8 27B Benchmark Results
Benchmark scores for Qwen3.8-27B.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSWE-MM | Score38.60% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWebArena-Verified | Score64.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBabyVision | Score85.60% | Rank02 | Participants11 | Percentile90.00% | EvidenceC | Evaluated |
| BenchmarkQwenSWEBench | Score79.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Multimodal | Score38.60% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkClawEval-MM | Score56.90% | Rank03 | Participants6 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score84.30% | Rank03 | Participants24 | Percentile91.30% | EvidenceC | Evaluated |
| BenchmarkRecreationBench | Score47.10% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAndroidWorld | Score81.90% | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkCoWorkBench | Score70.70% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkMathVision | Score94.60% | Rank04 | Participants35 | Percentile91.18% | EvidenceC | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score91.10% | Rank04 | Participants18 | Percentile82.35% | EvidenceC | Evaluated |
| BenchmarkVision2Web | Score62.90% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench v6 | Score90.30% | Rank05 | Participants62 | Percentile93.44% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score90.20% | Rank06 | Participants55 | Percentile90.74% | EvidenceC | Evaluated |
| BenchmarkRealWorldQA | Score85.90% | Rank07 | Participants31 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score42.90% | Rank08 | Participants16 | Percentile53.33% | EvidenceC | Evaluated |
| BenchmarkIFBench | Score79.50% | Rank08 | Participants39 | Percentile81.58% | EvidenceC | Evaluated |
| BenchmarkJob Bench | Score33.40% | Rank08 | Participants8 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkERQA | Score65.50% | Rank09 | Participants26 | Percentile68.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,593.73 rating | Rank14 | Participants97 | Percentile86.46% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Pro | Score61.70% | Rank15 | Participants55 | Percentile74.07% | EvidenceC | Evaluated |
| BenchmarkNL2Repo | Score42.30% | Rank16 | Participants22 | Percentile28.57% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score6.98% | Rank16 | Participants49 | Percentile68.75% | EvidenceA | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score73.00% | Rank21 | Participants35 | Percentile41.18% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,279.32 rating | Rank22 | Participants107 | Percentile80.19% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score1.03% | Rank25 | Participants49 | Percentile50.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score0.78% | Rank25 | Participants49 | Percentile50.00% | EvidenceA | Evaluated |
| BenchmarkDeepSWE 1.1 | Score42.20% | Rank26 | Participants31 | Percentile16.67% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score-0.39% | Rank26 | Participants49 | Percentile47.92% | EvidenceA | Evaluated |
Qwen3.8 27B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenawebdev | Categoryimage to webdev | Rank07 | Rating / score1,573.50 | Votes1,686 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank14 | Rating / score1,593.73 | Votes3,543 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank14 | Rating / score1,593.73 | Votes3,543 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank14 | Rating / score1,599.58 | Votes2,403 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank15 | Rating / score1,583.79 | Votes389 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank16 | Rating / score0.07 | VotesN/A | Observations13.9K | Result date |
| Arenatext | Categoryexpert | Rank21 | Rating / score1,491.33 | Votes712 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank22 | Rating / score1,279.32 | Votes2,954 | ObservationsN/A | Result date |
| Arenaagent | Categoryoverall | Rank25 | Rating / score0.01 | VotesN/A | Observations2.4M | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank25 | Rating / score0.01 | VotesN/A | Observations5.6K | Result date |
| Arenavision | Categoryocr | Rank25 | Rating / score1,283.62 | Votes1,959 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank26 | Rating / score0.00 | VotesN/A | Observations15.3K | Result date |
| Arenavision | Categorydiagram | Rank27 | Rating / score1,285.58 | Votes714 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank29 | Rating / score1,470.13 | Votes1,070 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank29 | Rating / score1,271.79 | Votes958 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank30 | Rating / score1,259.89 | Votes251 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank31 | Rating / score1,263.61 | Votes1,959 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank33 | Rating / score1,502.99 | Votes417 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank33 | Rating / score1,475.14 | Votes2,802 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank33 | Rating / score1,464.15 | Votes289 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank33 | Rating / score1,251.49 | Votes2,954 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry business and management and financial operations | Rank34 | Rating / score1,442.12 | Votes1,340 | ObservationsN/A | Result date |
| Arenaagent bash recovery steps | Categoryoverall | Rank35 | Rating / score-0.02 | VotesN/A | Observations98.4K | Result date |
| Arenatext | Categoryinstruction following | Rank35 | Rating / score1,441.70 | Votes2,414 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank35 | Rating / score1,454.82 | Votes3,196 | ObservationsN/A | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank36 | Rating / score0.00 | VotesN/A | Observations2.3M | Result date |
| Arenatext | Categoryfrench | Rank36 | Rating / score1,466.30 | Votes237 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank36 | Rating / score1,270.69 | Votes714 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank37 | Rating / score1,476.91 | Votes2,006 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank37 | Rating / score1,489.47 | Votes2,788 | ObservationsN/A | Result date |
Qwen3.8 27B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.10 input, $0.40 output per 1M via RunInfra
- Tracked offerings
- 31
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderHetzner | Provider model IDQwen3.8-27B | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderOVHcloud AI Endpoints | Provider model IDqwen3.8-27b | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context262.1K | Updated |
| ProviderRunInfra | Provider model IDQwen/Qwen3.8-27B | Regionglobal | Input / 1M$0.10 | Output / 1M$0.40 | Context262.1K | Updated |
| ProviderNanoGPT | Provider model IDqwen3.8-27b | Regionglobal | Input / 1M$0.15 | Output / 1M$0.70 | Context262.1K | Updated |
| ProviderEmpirioLabs AI | Provider model IDqwen3-8-27b | Regionglobal | Input / 1M$0.17 | Output / 1M$0.50 | Context262.1K | Updated |
| ProviderCrofAI | Provider model IDqwen3.8-27b | Regionglobal | Input / 1M$0.20 | Output / 1M$1.5 | Context262.1K | Updated |
| ProviderLLM Tech | Provider model IDunsloth/Qwen3.8-27B-NVFP4 | Regionglobal | Input / 1M$0.25 | Output / 1M$2.09 | Context262.1K | Updated |
| ProviderIteraCompute | Provider model IDiteracompute/qwen3.8-27b | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context327.7K | Updated |
| ProviderAKI.IO | Provider model IDqwen3.8-27b | Regionglobal | Input / 1M$0.30 | Output / 1M$2.2 | Context262.1K | Updated |
| ProviderOrcaRouter | Provider model IDqwen/qwen3.8-27b | Regionglobal | Input / 1M$0.33 | Output / 1M$2.4 | Context262.1K | Updated |
| ProviderCortecs | Provider model IDqwen3.8-27b | Regionglobal | Input / 1M$0.334 | Output / 1M$2.45 | Context262.1K | Updated |
| ProviderKosmik Compute | Provider model IDqwen/qwen3.8-27b | Regionglobal | Input / 1M$0.35 | Output / 1M$2.2 | Context262.1K | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3.8-27B | Regionglobal | Input / 1M$0.40 | Output / 1M$3 | Context262.1K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3.8-27B | Regionglobal | Input / 1M$0.40 | Output / 1M$3 | Context262.1K | Updated |
| Providerai& | Provider model IDqwen/qwen3.8-27b | Regionglobal | Input / 1M$0.40 | Output / 1M$3 | Context262.1K | Updated |
| ProviderWeights & Biases | Provider model IDQwen/Qwen3.8-27B | Regionglobal | Input / 1M$0.40 | Output / 1M$3 | Context262.1K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDQwen3.8-27B | Regionglobal | Input / 1M$0.41 | Output / 1M$2.5 | Context32.8K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3.8-27b | Regionglobal | Input / 1M$0.42 | Output / 1M$3 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3.8-27b | Regionglobal | Input / 1M$0.425 | Output / 1M$2.55 | Context1M | Updated |
| ProviderNeuralwatt | Provider model IDqwen-3.8-27b | Regionglobal | Input / 1M$0.45 | Output / 1M$3.2 | Context262.1K | Updated |
| ProviderCloudflare Workers AI | Provider model ID@cf/qwen/qwen3.8-27b | Regionglobal | Input / 1M$0.45 | Output / 1M$3.2 | Context262.1K | Updated |
| ProviderOfox | Provider model IDbailian/qwen3.8-27b | Regionglobal | Input / 1M$0.45 | Output / 1M$3.2 | Context1.1M | Updated |
| ProviderVenice AI | Provider model IDqwen-3-8-27b | Regionglobal | Input / 1M$0.45 | Output / 1M$3.2 | Context262.1K | Updated |
| ProviderBerget.AI | Provider model IDQwen/Qwen3.8-27B-FP8 | Regionglobal | Input / 1M$0.46 | Output / 1M$3.48 | Context262.1K | Updated |
| ProviderCharm Hyper | Provider model IDqwen3.8-27b | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen3.8-27b | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderEden AI | Provider model IDqwen/qwen3.8-27b | Regionglobal | Input / 1M$0.50 | Output / 1M$3 | Context1M | Updated |
| ProviderRegolo AI | Provider model IDqwen3.8-27b | Regionglobal | Input / 1M$0.58 | Output / 1M$2.42 | Context120K | Updated |
| ProviderGroq | Provider model IDqwen/qwen3.8-27b | Regionglobal | Input / 1M$0.80 | Output / 1M$4 | Context131K | Updated |
| Providerevroc | Provider model IDQwen/Qwen3.8-27B | Regionglobal | Input / 1M$0.87 | Output / 1M$3.5 | Context262.1K | Updated |
Qwen3.8 27B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3.8-27B. 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.
Qwen3.8 27B Specifications
Technical details for the model's default version.
- Version
- Qwen3.8-27B
- Released
- Aug 14, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 27.8B
- Context window
- 262.1K
- Max output
- 131.1K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3.8 27B 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 |
|---|
| VersionQwen3.8-27B | Released | LLMBoard74.94 | Parameters27.8B | Context262.1K | Max output131.1K | Open weightsYes | LicenseApache 2.0 |
Models similar to Qwen3.8 27B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3.7 Max
Alibaba Cloud / Qwen Team
AC
Qwen3.7 Plus
Alibaba Cloud / Qwen Team
AC
Qwen3.8 Flash
Alibaba Cloud / Qwen Team
AC
Qwen3.8 Flash Next
Alibaba Cloud / Qwen Team
AC
Qwen3.6 Plus
Alibaba Cloud / Qwen Team
AC
Qwen3.5 397B A17B
Alibaba Cloud / Qwen Team
What is Qwen3.8 27B?
Key information about Qwen3.8 27B and its available data.
8 27B is a multimodal large language model that understands text, images, and video. 0 license.
Data as of 2026-09-08.
FAQ
Common questions about Qwen3.8 27B.
When was Qwen3.8 27B released?
Qwen3.8 27B's default version was released on Aug 14, 2026.
How much does Qwen3.8 27B cost?
No official standard PAYG price is currently available for Qwen3.8 27B. The lowest tracked third-party offer starts at $0.10 input and $0.40 output via RunInfra.
Who created Qwen3.8 27B?
Qwen3.8 27B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3.8 27B?
The default version has a 262.1K token context window.
Is Qwen3.8 27B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Qwen3.8 27B?
31 provider offerings are linked to the default version.