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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SciEval - Astronomy | 75.64 | Astronomy (%) | 100 |
| SGI-Bench Wet Experiment | 33.62 | Wet Experiment Score | 94.4 |
| LOM Benchmark - CycleDetection | 93 | Accuracy (%) | 91.7 |
| LLM Arena RU | 1113 | Arena Elo | 89 |
| SGI-Bench | 31.97 | SGI-Score | 88.9 |
| SciEval - Physics | 41.04 | Physics (%) | 88.9 |
| BenchTable | 72.3 | Total Score (%) | 88.7 |
| UGI - Natural Intelligence | 43.8 | NatInt Score | 88.7 |
| SnakeBench | 30.8 | TrueSkill Rating | 88.2 |
| AA MMLU-Pro | 84.12 | Accuracy (%) | 88.1 |
| AA LiveCodeBench | 76.72 | Pass@1 (%) | 88 |
| Kagi LLM Benchmark | 72.5 | Accuracy (%) | 85.7 |
Interactive version: theaggregate.ai/model?slug=qwen-3-max · How the rankings work · Data refreshed daily, snapshot 2026-07-22.