llm.ing

Qwen3-Next 80B-A3B Instruct

Alibabaopen weightsOpenRouter ↗Hugging Face ↗Artificial Analysis ↗

Qwen instruction model for multilingual chat, reasoning, and tool use

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Intelligence Indexintelligence9.6—independentaaSep 9, 2026
9.6—mirroropenrouterOct 5, 2026
LMArena Textpreference1417—crowdlmarenaNov 9, 2026
Median output speedspeed151 tok/s—independentaaNov 19, 2026
Median time to first tokenspeed0.80s—independentaaNov 18, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
DeepInfrafp8262K$0.09 · $1.198.37%——
Google—262K$0.15 · $1.297.34%——
Parasailfp8262K$0.1 · $1.1100.00%——