Alibaba Cloud / Qwen Team model product
Qwen3.5 0.8B
8 billion parameter vision-language model using Gated DeltaNet hybrid architecture with a 3:1 ratio of linear attention to full softmax attention.
Updated Aug 12, 2026. Default version: Qwen3.5-0.8B
LLMBoard score0.0Qwen3.5-0.8B
Coverage60%20 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Qwen3.5 0.8B Specifications
Technical details for the model's default version.
- Version
- Qwen3.5-0.8B
- Released
- Mar 2, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 800M
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
Qwen3.5 0.8B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3.5 0.8B Benchmark Results
Benchmark scores for Qwen3.5-0.8B.
| MAXIFE | 39.2% | 11 | 11 | 0.0% | C | |
| NOVA-63 | 42.4% | 11 | 11 | 0.0% | C | |
| BFCL-V4 | 25.3% | 13 | 13 | 0.0% | C | |
| Global PIQA | 59.4% | 13 | 13 | 0.0% | C | |
| AA-LCR | 4.7% | 16 | 16 | 0.0% | C | |
| C-Eval | 50.5% | 17 | 18 | 5.9% | C | |
| LongBench v2 | 26.1% | 17 | 17 | 0.0% | C | |
| PolyMATH | 8.2% | 23 | 23 | 0.0% | C | |
| t2-bench | 11.6% | 23 | 23 | 0.0% | C | |
| WMT24++ | 27.2% | 23 | 23 | 0.0% | C | |
| MMLU-ProX | 34.6% | 28 | 32 | 12.9% | C | |
| Multi-Challenge | 18.9% | 28 | 29 | 3.6% | C | |
| IFBench | 21.0% | 29 | 29 | 0.0% | C | |
| Include | 40.6% | 29 | 31 | 6.7% | C | |
| SuperGPQA | 21.3% | 34 | 34 | 0.0% | C | |
| MMLU-Redux | 59.5% | 47 | 48 | 2.1% | C | |
| MMMLU | 44.3% | 49 | 49 | 0.0% | C | |
| IFEval | 44.0% | 65 | 65 | 0.0% | C | |
| MMLU-Pro | 42.3% | 124 | 129 | 3.9% | C | |
| GPQA | 11.9% | 234 | 234 | 0.0% | C |
Qwen3.5 0.8B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Qwen3.5 0.8B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3.5-0.8B. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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 0.8B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 1
| QVAC | qwen3.5-0.8b | global | N/A | N/A | 32.8K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3.5 0.8B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Qwen3.5-0.8B | 0.0 | 800M | N/A | N/A | No | Apache 2.0 |
What is Qwen3.5 0.8B?
Key information about Qwen3.5 0.8B and its available data.
8 billion parameter vision-language model using Gated DeltaNet hybrid architecture with a 3:1 ratio of linear attention to full softmax attention. It supports 262K native context length and features both thinking and non-thinking modes.
Data as of 2026-08-11.
Qwen3.5 0.8B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen3.5 0.8B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen2.5 Coder 7B
Alibaba Cloud / Qwen Team
AC
Qwen2 7B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 2B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 Coder 32B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 7B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 14B
Alibaba Cloud / Qwen Team
FAQ
Common questions about Qwen3.5 0.8B.
When was Qwen3.5 0.8B released?
Qwen3.5 0.8B's default version was released on Mar 2, 2026.
How much does Qwen3.5 0.8B cost?
No official standard PAYG price is currently available for Qwen3.5 0.8B.
Who created Qwen3.5 0.8B?
Qwen3.5 0.8B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3.5 0.8B?
A context window is not available for the default version.
Is Qwen3.5 0.8B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Qwen3.5 0.8B?
1 provider offerings are linked to the default version.
What models should I compare Qwen3.5 0.8B with?
Nearby ranked alternatives include GPT-3.5-Turbo, Phi 3.5 mini, Gemini 1.5 Flash 8B.