llm.ing

Qwen3.5 122B-A10B

Alibabaopen weightsOpenRouter ↗Hugging Face ↗Artificial Analysis ↗

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

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Agentic Indexagentic20.7mirroropenrouterJul 23, 2026
15.8non-reasoningindependentaaJul 24, 2026
20.7independentaaJul 24, 2026
AA Coding Indexcoding45.7mirroropenrouterJul 23, 2026
43.3non-reasoningindependentaaJul 24, 2026
45.7independentaaJul 24, 2026
AA Intelligence Indexintelligence32.3mirroropenrouterJul 23, 2026
27.6non-reasoningindependentaaJul 24, 2026
32.3independentaaJul 24, 2026
LMArena Textpreference1432crowdlmarenaJul 21, 2026
LMArena Visionpreference1246crowdlmarenaJul 21, 2026
LMArena WebDevpreference1364crowdlmarenaJul 21, 2026
Median output speedspeed145 tok/snon-reasoningindependentaaJul 24, 2026
134 tok/sindependentaaJul 24, 2026
Median time to first tokenspeed2.36snon-reasoningindependentaaJul 24, 2026
2.37sindependentaaJul 24, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Alibaba262K$0.26 · $2.0882.33%
AtlasCloudfp8262K$0.3 · $2.486.90%
DeepInfrafp4262K$0.29 · $2.481.86%
Novitabf16262K$0.4 · $3.293.56%
SiliconFlowfp8262K$0.26 · $2.0852.00%