geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk

COMPARE.

AI
Filters

Filter AI models

Brand
Benchmark coverage
Clear all filters

Best result per entry; configurations may differ.

Type
5 results Benchmark score
alibaba

Qwen 3.6 35B-A3B

Models
Context window
262,144 tokens*
Maximum output
65,536 tokens*
Open weights
Yes*
Reasoning
Yes*
SimpleVQA · version unreported · reported score#1* · 58.90*Platform unreported
ECI 143.8*General capability index
alibaba

Qwen3.5 35B-A3B

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
Yes
SimpleVQA · version unreported · reported score#2* · 58.30*Platform unreported
Arena 1394.5Human preference · 30,427 votes
anthropic

Claude Sonnet 4.5

Models
Context window
200,000 tokens
Maximum output
64,000 tokens
Open weights
No
Maximum input
200,000 tokens*
SimpleVQA · version unreported · reported score#3* · 57.60*Platform unreported
Arena 1434.6Human preference · 83,940 votes
alibaba

Qwen3.5 27B

Models
Context window
262,144 tokens
Maximum output
65,536 tokens
Open weights
Yes
Reasoning
Yes
SimpleVQA · version unreported · reported score#4* · 56*Platform unreported
Arena 1409.0Human preference · 28,647 votes
google

Gemma 4 26B A4B

Models
Context window
262,144 tokens
Open weights
Yes
Checkpoint tensor payload
48.07 GiB
Architecture
gemma4
SimpleVQA · version unreported · reported score#5* · 52.20*Platform unreported
ECI 142.0*General capability index

* Provisional data