Qwen3.5-27B
Released
2026-02-24
Last refreshed
2026-06-29
Status
Researched 113d ago
Open sourceCommercial use: permittedMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use
Qwen3.5-27B is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 262k context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
Specifications
- Family
- Qwen3.5
- Released
- 2026-02-24
- Context
- 262k
- Parameters
- 27B
- Architecture
- Decoder Only
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
Created by
Pricing
Output / 1M
$1.56
Input / 1M
$0.195
Cheapest of 4 routes · Alibaba Cloud PAI-EAS
Links
About
Open-weight dense 27B multimodal Qwen3.5 model with native vision-language support. Apache 2.0.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ C2 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ B3 relevant benchmarks in the decision map.
Provider price ladder
Compare all 4Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Alibaba Cloud PAI-EAS | $0.195 | $1.56 | Serverless |
| OpenRouter | $0.195 | $1.56 | Serverless |
| Novita AI | $0.300 | $2.40 | Serverless |
| DeepInfra | $0.260 | $2.60 | Serverless |
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured Outputs
Benchmark peer barsfor Coding
SWE-bench VerifiedRank 55 of 81
LiveCodeBenchRank 25 of 56
Benchmark scores(9)
Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Google-Proof Q&A | 85.8 | diamondObserved 2026-04-18 | — | Source |
| MMMU Pro | 75.0 | LLM-Stats aggregatorObserved 2026-06-07 | — | Source |
| SWE-rebench | 58.9 | pass@1 (best of 5 runs)Observed 2026-05-28 | — | Source |
| Berkeley Function Calling Leaderboard v3 | 68.5 | BFCL-V4 (newest BFCL version), from official model card (accuracy)Observed 2026-06-07 | — | Source |
| Humanity's Last Exam | 24.3 | HLE with CoT (no tools), from official model card (accuracy)Observed 2026-06-07 | — | Source |
| LiveCodeBench | 80.7 | LiveCodeBench v6 (pass@1)Observed 2026-06-07 | — | Source |
| MMLU PRO | 86.1 | From official HuggingFace model card benchmark table (accuracy)Observed 2026-06-07 | — | Source |
| SWE-bench Verified | 72.4 | From official model card (resolved)Observed 2026-06-07 | — | Source |
| τ-bench | 79.0 | TAU2-Bench, from official model card (accuracy)Observed 2026-06-07 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(3)
Compare Qwen3.5-27B with other models
Comparison and alternatives
Browse all comparisons →Qwen3.5-27B vs Qwen3.6-27BQwen3.5-27B vs DeepSeek V4 FlashQwen3.5-27B vs Qwen3.6-35B-A3BQwen3.5-27B vs DeepSeek V4 ProQwen3.5-27B vs Claude Sonnet 4.6Qwen3.5-27B vs DeepSeek R1Qwen3.5-27B vs Claude Opus 4.7Qwen3.5-27B vs Claude Opus 4.6Qwen3.5-27B vs Qwen3.5-397B-A17BQwen3.5-27B vs Grok 4Qwen3.5-27B vs DeepSeek V3Qwen3.5-27B vs GLM-5.1Qwen3.5-27B vs GPT-5.5Qwen3.5-27B vs Llama 3 70B InstructQwen3.5-27B vs Llama 3.2 1B InstructQwen3.5-27B vs Grok-3
Show all 22 popular comparisonssorted by 7-day search impressions
Qwen3.5-27B vs Gemini 2.5 Flash38Qwen3.5-27B vs Claude 3.7 Sonnet37Qwen3.5-27B vs Kimi K2.519Qwen3.5-27B vs Mixtral 8x7B18Qwen3.5-27B vs Mistral Nemotron17Qwen3.5-27B vs Claude Opus 4.515Qwen3.5-27B vs GLM-5 9B13Qwen3.5-27B vs Mixtral 8x7B Instruct v0.112Qwen3.5-27B vs Gemini 2.5 Pro11Qwen3.5-27B vs GLM-58Qwen3.5-27B vs Mistral Large 2 (2407)6Qwen3.5-27B vs o34Qwen3.5-27B vs Mistral Large 24Qwen3.5-27B vs GLM-5 Turbo3Qwen3.5-27B vs GPT-5.23Qwen3.5-27B vs o3 Mini2Qwen3.5-27B vs GLM-5V-Turbo2Qwen3.5-27B vs Gemini 2.5 Pro Preview 05-061Qwen3.5-27B vs GPT-5.41Qwen3.5-27B vs Claude Haiku 4.51Qwen3.5-27B vs Llama 3 8B Instruct0Qwen3.5-27B vs Claude Sonnet 4.50
Created by
Pricing
Output / 1M
$1.56
Input / 1M
$0.195
Cheapest of 4 routes · Alibaba Cloud PAI-EAS
Links