Alibaba Cloud / Qwen Team model product
Qwen3.7 Plus
7 Plus is a multimodal agent model from Alibaba Cloud / Qwen Team for vision-and-language interaction, coding, GUI and CLI operation, and visual question answering.
Updated Oct 23, 2026. Default version: Qwen3.7-Plus
LLMBoard Score71.0Qwen3.7-Plus
Coverage100%59 benchmark families
Context window1MTokens
Official input price$0.40Alibaba API
Qwen3.7 Plus Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3.7 Plus Benchmark Results
Benchmark scores for Qwen3.7-Plus.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBC-VL | Score51.10% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCountQA | Score77.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkDeepPlanning | Score62.30% | Rank01 | Participants10 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHiPhO | Score84.10% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLingoQA | Score83.40% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMedXpertQA-MM | Score71.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMLVU | Score87.40% | Rank01 | Participants10 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMBC | Score46.30% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMSearch-Plus | Score41.40% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 | Score91.70% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOCRBench_V2 | Score67.10% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkQwenClawBench | Score61.80% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkQwenWorldBench | Score62.10% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSURDS | Score77.20% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVLADBench | Score77.20% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkWorldVQA | Score61.10% | Rank01 | Participants7 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkApex | Score22.70% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score94.60% | Rank02 | Participants70 | Percentile98.55% | EvidenceC | Evaluated |
| BenchmarkMAXIFE | Score88.80% | Rank02 | Participants12 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkMMLU-ProX | Score85.40% | Rank02 | Participants33 | Percentile96.88% | EvidenceC | Evaluated |
| BenchmarkODinW | Score51.10% | Rank02 | Participants16 | Percentile93.33% | EvidenceC | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score91.40% | Rank02 | Participants20 | Percentile94.74% | EvidenceC | Evaluated |
| BenchmarkPolyMATH | Score84.00% | Rank02 | Participants23 | Percentile95.45% | EvidenceC | Evaluated |
| BenchmarkSimpleVQA | Score0.82 points | Rank02 | Participants17 | Percentile93.75% | EvidenceC | Evaluated |
| BenchmarkTVBench | Score78.20% | Rank02 | Participants5 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkMCP-Mark | Score58.70% | Rank03 | Participants9 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkNOVA-63 | Score58.80% | Rank03 | Participants12 | Percentile81.82% | EvidenceC | Evaluated |
| BenchmarkSuperGPQA | Score71.40% | Rank03 | Participants37 | Percentile94.44% | EvidenceC | Evaluated |
| BenchmarkVideo-MME | Score88.00% | Rank03 | Participants17 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkVisFactor | Score42.80% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
Qwen3.7 Plus Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categorypolish | Rank19 | Rating / score1,438.86 | Votes480 | ObservationsN/A | Result date |
| Arenaagent bash reliability | Categoryoverall | Rank22 | Rating / score0.02 | VotesN/A | Observations23.5K | Result date |
| Arenatext | Categorygerman | Rank24 | Rating / score1,470.53 | Votes763 | ObservationsN/A | Result date |
| Arenadocument | Categoryoverall | Rank25 | Rating / score1,444.14 | Votes4,591 | ObservationsN/A | Result date |
| Arenadocument style control | Categoryoverall | Rank25 | Rating / score1,452.54 | Votes4,591 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank25 | Rating / score1,331.64 | Votes740 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank27 | Rating / score1,312.14 | Votes740 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank28 | Rating / score1,468.36 | Votes1,939 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank28 | Rating / score1,280.36 | Votes5,067 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank29 | Rating / score1,487.39 | Votes2,506 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank29 | Rating / score1,410.70 | Votes454 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank29 | Rating / score1,457.50 | Votes1,067 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank29 | Rating / score1,288.49 | Votes9,923 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank29 | Rating / score1,278.15 | Votes14,212 | ObservationsN/A | Result date |
| Arenaagent bash reliability no prereq | Categoryoverall | Rank29 | Rating / score-0.01 | VotesN/A | Observations12.1K | Result date |
| Arenavision | Categorydiagram | Rank30 | Rating / score1,291.64 | Votes3,752 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank31 | Rating / score1,511.55 | Votes2,269 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank31 | Rating / score1,462.91 | Votes1,651 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank31 | Rating / score1,280.42 | Votes9,923 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank32 | Rating / score-0.09 | VotesN/A | Observations15.4K | Result date |
| Arenatext | Categoryfrench | Rank32 | Rating / score1,471.91 | Votes1,611 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank32 | Rating / score1,457.32 | Votes4,659 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank32 | Rating / score1,467.75 | Votes4,106 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank32 | Rating / score1,294.73 | Votes1,646 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank32 | Rating / score1,263.31 | Votes14,212 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank33 | Rating / score1,263.72 | Votes5,067 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank34 | Rating / score1,508.86 | Votes2,662 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank34 | Rating / score1,290.45 | Votes3,752 | ObservationsN/A | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank35 | Rating / score-0.10 | VotesN/A | Observations6.6K | Result date |
| Arenatext | Categorynon english | Rank35 | Rating / score1,444.79 | Votes24,327 | ObservationsN/A | Result date |
Qwen3.7 Plus Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.40 input, $1.6 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.228 input, $0.92 output per 1M via 302.AI
- Tracked offerings
- 33
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAlibaba Token Plan | Provider model IDqwen3.7-plus | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAlibaba Coding Plan (China) | Provider model IDqwen3.7-plus | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAlibaba Coding Plan | Provider model IDqwen3.7-plus | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| ProviderAlibaba Token Plan (China) | Provider model IDqwen3.7-plus | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1M | Updated |
| Provider302.AI | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.228 | Output / 1M$0.92 | Context1M | Updated |
| ProviderAlibaba (China) | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.276 | Output / 1M$1.1 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.282 | Output / 1M$1.13 | Context991K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.32 | Output / 1M$1.28 | Context1M | Updated |
| ProviderCrossModel | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.32 | Output / 1M$1.25 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDalibaba/qwen3.7-plus | Regionglobal | Input / 1M$0.32 | Output / 1M$1.28 | Context1M | Updated |
| ProviderRequesty | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.32 | Output / 1M$1.28 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.32 | Output / 1M$1.28 | Context1M | Updated |
| ProviderPioneer | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.32 | Output / 1M$1.28 | Context1M | Updated |
| ProviderStandard Compute | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.32 | Output / 1M$1.28 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.35 | Output / 1M$1.42 | Context1M | Updated |
| ProviderKenari | Provider model IDqwen3-7-plus | Regionglobal | Input / 1M$0.3829 | Output / 1M$1.49 | Context1M | Updated |
| ProviderImpossibl | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderOpenCode Go | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDalibaba/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context983.6K | Updated |
| ProviderLLMTR | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderAlibaba | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderZenMux | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderOfox | Provider model IDbailian/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderClinePass | Provider model IDcline-pass/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderEmpirioLabs AI | Provider model IDqwen3-7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context983.6K | Updated |
| ProviderOfox | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context1.1M | Updated |
| ProviderNanoGPT | Provider model IDqwen/qwen3.7-plus | Regionglobal | Input / 1M$0.40 | Output / 1M$1.6 | Context991.8K | Updated |
Qwen3.7 Plus Runtime Performance
Provider-specific output speed and catalog latency for Qwen3.7-Plus. 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.
Qwen3.7 Plus Specifications
Technical details for the model's default version.
- Version
- Qwen3.7-Plus
- Released
- May 31, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Qwen3.7 Plus 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 |
|---|
| VersionQwen3.7-Plus | Released | LLMBoard70.97 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
Models similar to Qwen3.7 Plus
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3.8 27B
Alibaba Cloud / Qwen Team
AC
Qwen3.7 Max
Alibaba Cloud / Qwen Team
AC
Qwen3.6 Plus
Alibaba Cloud / Qwen Team
AC
Qwen3.5 397B A17B
Alibaba Cloud / Qwen Team
AC
Qwen3.8 Omni Flash
Alibaba Cloud / Qwen Team
AC
Qwen3.8 Flash
Alibaba Cloud / Qwen Team
What is Qwen3.7 Plus?
Key information about Qwen3.7 Plus and its available data.
7 text backbone, with full-modality input, a 1 million token context window, and up to 65,536 output tokens.
It supports visual scene and screen understanding, GUI and CLI interaction, mobile app navigation, code generation from visual references, and search-augmented visual questions, and is available through Alibaba Cloud Model Studio (DashScope).
Data as of 2026-10-22.
FAQ
Common questions about Qwen3.7 Plus.
When was Qwen3.7 Plus released?
Qwen3.7 Plus's default version was released on May 31, 2026.
How much does Qwen3.7 Plus cost?
Qwen3.7 Plus's official API price is $0.40 per million input tokens and $1.6 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.228 input and $0.92 output via 302.AI.
Who created Qwen3.7 Plus?
Qwen3.7 Plus was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3.7 Plus?
The default version has a 1M token context window.
Is Qwen3.7 Plus open weight?
No. The default version is not marked as having publicly available weights.