llm.ing

Qwen3.5 35B-A3B

Alibabaopen weightsOpenRouter ↗Hugging Face ↗Artificial Analysis ↗

Qwen vision-language model for visual reasoning, documents, and agent tasks

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Agentic Indexagentic11.8mirroropenrouterJul 23, 2026
AA Coding Indexcoding37.0mirroropenrouterJul 23, 2026
AA Intelligence Indexintelligence24.3mirroropenrouterAug 7, 2026
19.3independentaaSep 9, 2026
LMArena Textpreference1395crowdlmarenaSep 13, 2026
LMArena WebDevpreference1250crowdlmarenaSep 11, 2026
Median output speedspeed147 tok/sindependentaaSep 21, 2026
Median time to first tokenspeed2.09sindependentaaSep 21, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Alibaba262K$0.163 · $1.398.50%
AtlasCloudfp8262K$0.225 · $1.899.39%
Darkbloomfp4262K$0.08 · $0.7599.93%
DeepInfrafp8262K$0.14 · $199.96%
Parasailfp8262K$0.15 · $199.77%
SiliconFlowfp8262K$0.24 · $1.867.16%
Venice256K$0.313 · $1.2599.97%