Skip to content

Qwen3.8-27B vs Qwen3.5-35B-A3B

Qwen3.8-27B leads on the Visual Intelligence Index by 2.7 points, and Qwen3.8-27B scores higher on 6 of the 7 benchmarks where the two differ.

At a glance

MeasureQwen3.8-27BQwen3.5-35B-A3B
Visual Intelligence Index68.5%65.7%
Rank#6 of 9#7 of 9
Cost per taskMean over the benchmarks, at list price.——
Latency per taskEach benchmark's median, averaged.32.0s14.3s
Tokens per task25,00925,755
Input / 1M tokens——
Output / 1M tokens——
Context window256K256K
AvailabilityOpen weightsOpen weights

How cost and latency are measured

Capabilities

Each capability index is a weighted mean of the benchmarks that contribute to the capability.

CapabilityQwen3.8-27BQwen3.5-35B-A3B
Perception67.8%65.3%
Spatial Reasoning68.6%65.8%
Temporal Reasoning68.4%65.5%
Action / Event Understanding65.2%62.2%
Causal Reasoning72.3%70.1%
Information Retrieval67.0%63.6%

Benchmarks

Usability

Qwen3.8-27B

4.5/ 5

Reachable1.0

There is an endpoint you can call without hosting anything.

  • First-party API — supported
  • Third-party API — supported
Portable1.0

You can run it yourself, and are not tied to one vendor.

  • Open weights — supported
  • Self-hostable — supported
Multimodal input1.0

It takes the footage directly, rather than frames you extracted.

  • Video ingestion — supported
  • Audio — supported
Programmable1.0

Output you can parse, and tools it can call on its own.

  • Structured output — supported
  • Tool calling — supported
Operable0.5

Usable interactively and in bulk, not only one call at a time.

  • Streaming — supported
  • Batch API — not supported

Qwen3.5-35B-A3B

4.5/ 5

Reachable1.0

There is an endpoint you can call without hosting anything.

  • First-party API — supported
  • Third-party API — supported
Portable1.0

You can run it yourself, and are not tied to one vendor.

  • Open weights — supported
  • Self-hostable — supported
Multimodal input1.0

It takes the footage directly, rather than frames you extracted.

  • Video ingestion — supported
  • Audio — supported
Programmable1.0

Output you can parse, and tools it can call on its own.

  • Structured output — supported
  • Tool calling — supported
Operable0.5

Usable interactively and in bulk, not only one call at a time.

  • Streaming — supported
  • Batch API — not supported