Qwen Max (04-03): benchmark results
Provider: Alibaba. Released 2025-04-28. Access: API.
Aggregate Rating 1532 ± 23, rank #1927 of 10916 rated models, from 65 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Language - Chinese Semantic Understanding - Chinese (CompassBench 2404) | 78.3 | Score (%) | 100 |
| OpenCompass Language - Content Critique - English (CompassBench 2404) | 52 | Score (%) | 100 |
| OpenCompass Subjective - Creation (CompassBench 2404) | 69.6 | Score (%) | 100 |
| OpenCompass Agent - CIBench - English (CompassBench 2404) | 69 | Score (%) | 96.7 |
| OpenCompass LLM - Agent - English (CompassBench 2404) | 76.6 | Score (%) | 96.7 |
| OpenCompass LLM - Reasoning (CompassBench 2404) | 49.6 | Score (%) | 96.7 |
| OpenCompass Language - Intention Recognition - English (CompassBench 2404) | 83.3 | Score (%) | 96.7 |
| OpenCompass Reasoning - Common Sense - Chinese (CompassBench 2404) | 52.9 | Score (%) | 96.7 |
| OpenCompass Language - Traditional Cultural Understanding - Chinese (CompassBench 2404) | 65.3 | Score (%) | 95 |
| OpenCompass Subjective - Average (CompassBench 2404) | 50 | Score (%) | 95 |
| OpenCompass Agent - T-Eval - Chinese (CompassBench 2404) | 81.1 | Score (%) | 93.3 |
| OpenCompass Agent - T-Eval - English (CompassBench 2404) | 84.2 | Score (%) | 93.3 |
Interactive version: theaggregate.ai/model?slug=qwen-max-04-03 · How It Works · Data refreshed daily, snapshot 2026-11-08.