Qwen 3 Max (Preview) — benchmark results
Alibaba's preview release of Qwen 3 Max. Provider: Alibaba. Released 2025-09-05. Access: API.
Unified ELO 1663 ± 13, rank #336 of 1776 rated models, from 53 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Wolfram LLM Benchmarking Project | 61.5 | Correct Functionality (%) | 91 |
| AA MMLU-Pro | 83.83 | Accuracy (%) | 87.5 |
| Chatbot Arena (Text) | 1435 | Elo | 80.1 |
| Vals AI TaxEval v2 | 73.96 | Accuracy (%) | 73.8 |
| AA Omniscience - Humanities & Social Sciences | 27.4 | Accuracy (%) | 73.4 |
| AA Omniscience - Software Engineering (SWE) - Java | 25 | Accuracy (%) | 73 |
| AA Omniscience - Law | 17.9 | Accuracy (%) | 72.9 |
| AA Omniscience - Software Engineering (SWE) - PHP | 38 | Accuracy (%) | 72.8 |
| AA Omniscience - Software Engineering (SWE) - Python | 31.5 | Accuracy (%) | 71.9 |
| AA LiveCodeBench | 65.08 | Pass@1 (%) | 71.8 |
| AA Omniscience - Software Engineering (SWE) - C | 50 | Accuracy (%) | 70.8 |
| AA AIME 2025 | 75 | Accuracy (%) | 70.6 |
Interactive version: theaggregate.ai/model?slug=qwen-3-max-preview · How the rankings work · Data refreshed daily, snapshot 2026-07-22.