all the models — AI benchmark observatory
← Models

Qwen3.5-0.8B

Alibaba Cloud / Qwen Team · open weight · qwen3.5-0.8b

Qwen3.5-0.8B is a 0.8 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.

IFEvalMMLU-ProGPQA

Benchmark scores

BenchmarkScore
IFEval0.44
MMLU-Pro0.42
GPQA0.12

Pricing

  • No provider pricing.

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.
Qwen3.5-0.8B Benchmarks · all the models