Qwen 3 Next 80B A3B — benchmark results

Alibaba Qwen 3 Next 80B A3B efficient MoE model (3B active). Provider: Alibaba. Released 2025-09-11. Access: Open.

Unified ELO 1739 ± 81, rank #212 of 1776 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
XDomainBench63.8R (k=1, Deterministic) (self-reported)100
Ko-AgentBench - L1 Single Tool Call77.27Argument Accuracy (%)92.9
Ko-AgentBench - L3 Sequential Tool Reasoning100PSM (%)82.1
Ko-AgentBench - L4 Parallel Tool Reasoning70Coverage (%)78.6
DVMap47.6Accuracy (self-reported)75
Ko-AgentBench - L5 Error Handling & Robustness25.42Adaptive Routing Score (%)64.3
Ko-AgentBench - L7 Long-Context Memory97.5Context Retention (%)57.1
Context Arena MRCR (2-needle)10.3AUC@1M (%)54.4
LLM2014 Logic 2025-1038.87Median Score51
BacktestBench44.06Overall Accuracy (OA) (self-reported)50
LLM2014 Logic 2025-1135.65Median Score44.2
LLM Chess (Saplin)-127.9ELO35

Interactive version: theaggregate.ai/model?slug=qwen-3-next-80b-a3b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.