Qwen 3 Max — benchmark results

Alibaba Qwen 3 Max model row. Provider: Alibaba. Released 2025-09-24. Access: API.

Unified ELO 1686 ± 13, rank #300 of 1776 rated models, from 170 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
SciEval - Astronomy75.64Astronomy (%)100
SGI-Bench Wet Experiment33.62Wet Experiment Score94.4
LOM Benchmark - CycleDetection93Accuracy (%)91.7
LLM Arena RU1113Arena Elo89
SGI-Bench31.97SGI-Score88.9
SciEval - Physics41.04Physics (%)88.9
BenchTable72.3Total Score (%)88.7
UGI - Natural Intelligence43.8NatInt Score88.7
SnakeBench30.8TrueSkill Rating88.2
AA MMLU-Pro84.12Accuracy (%)88.1
AA LiveCodeBench76.72Pass@1 (%)88
Kagi LLM Benchmark72.5Accuracy (%)85.7

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