Skip to content
Vision Index

Gemini 4 Argon vs Qwen3.5-35B-A3B

Gemini 4 Argon leads on the Visual Intelligence Index by 18.4 points, and Gemini 4 Argon scores higher on 6 of the 6 benchmarks where the two differ.

GoogleGemini 4 Argon84.1%Rank #1AlibabaQwen3.5-35B-A3B65.7%Rank #8

At a glance

MeasureGemini 4 ArgonQwen3.5-35B-A3B
Visual Intelligence Index84.1%65.7%
Rank#1 of 10#8 of 10
Cost per taskMean over the benchmarks, at list price.$0.110—
Latency per taskEach benchmark's median, averaged.23.9s14.3s
Tokens per task54,61425,755
Input / 1M tokens$2.00—
Output / 1M tokens$10.00—
Context window1.05M262K
AvailabilityProprietaryOpen weights

How cost and latency are measured

Capabilities

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

CapabilityGemini 4 ArgonQwen3.5-35B-A3B
Perception81.7%65.3%
Spatial Reasoning85.4%65.8%
Temporal Reasoning84.5%65.5%
Action / Event Understanding84.7%62.2%
Causal Reasoning85.4%70.1%
Information Retrieval82.7%63.6%

Benchmarks

BenchmarkGemini 4 ArgonQwen3.5-35B-A3B
Video-MME v277.0%42.5%
LVBench86.3%64.4%
Perception Test89.7%66.7%
NExT-QA90.0%83.4%
Q-Bench Video66.9%66.9%
EgoSchema86.4%77.2%
UCF101-AD81.8%41.3%

Usability

Gemini 4 Argon

4.0/ 5

Reachable1.0

There is an endpoint you can call without hosting anything.

  • First-party API — supported
  • Third-party API — supported
Portable0.0

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

  • Open weights — not supported
  • Self-hostable — not 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
Operable1.0

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

  • Streaming — supported
  • Batch API — 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