Qwen 3 Max (2026-01-23): benchmark results
January 23, 2026 Qwen 3 Max snapshot, tracked when sources report the dated API model. Provider: Alibaba. Released 2026-01-23. Access: API.
Aggregate Rating 1725 ± 15, rank #155 of 1656 rated models, from 69 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass LLM - Language (CompassBench 2601) | 89.4 | Score (%) | 100 |
| OpenCompass LLM - Math (CompassBench 2601) | 73.2 | Score (%) | 100 |
| OpenCompass Language - Dialogue (CompassBench 2601) | 98.9 | Score (%) | 100 |
| OpenCompass Language - NLP (CompassBench 2601) | 88.6 | Score (%) | 100 |
| OpenCompass Math - Competition (CompassBench 2601) | 70 | Score (%) | 98 |
| OpenCompass Code - Competition (CompassBench 2601) | 66.1 | Score (%) | 96 |
| OpenCompass Code - Comprehensive (CompassBench 2601) | 82.5 | Score (%) | 96 |
| OpenCompass LLM - Average (CompassBench 2601) | 74.4 | Score (%) | 96 |
| OpenCompass LLM - Code (CompassBench 2601) | 74.3 | Score (%) | 96 |
| OpenCompass Language - Instruction Following (CompassBench 2601) | 77.7 | Score (%) | 96 |
| OpenCompass Math - College (CompassBench 2601) | 76.3 | Score (%) | 96 |
| CorpFin v2 | 68.03 | Score (%) | 92.8 |
Interactive version: theaggregate.ai/model?slug=qwen-3-max-2026-01-23 · How It Works · Data refreshed daily, snapshot 2026-10-20.