Qwen 3.8 Max — benchmark results

Provider: Alibaba. Released 2026-08-03. Access: API.

Unified ELO 1910 ± 20, rank #49 of 1839 rated models, from 34 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Stats (ERQA)77.8Score (%)100
LLM Stats (HealthBench)60.2Score (%)100
LLM Stats (LongBench v2)66.3Score (%)100
LLM Stats (NL2Repo)55.9Score (%)100
LLM Stats (OSWorld-Verified)86.1Score (%)100
LLM Stats (SkillsBench)70.2Score (%)100
LLM Stats (VideoMME w sub.)90.4Score (%)100
LVBench81.8Score (self-reported)100
RealWorldQA88RealWorldQA (self-reported)100
Chatbot Arena (Vision)1305Arena Score99.3
Chatbot Arena (Text)1496Elo99
LLM Stats Score52.56LLM Stats Score (conservative rating)98.1

Interactive version: theaggregate.ai/model?slug=qwen-3-8-max · How It Works · Data refreshed daily, snapshot 2026-08-05.