Qwen Max (04-28): benchmark results
Provider: Alibaba. Released 2025-04-28. Access: API.
Aggregate Rating 1554 ± 20, rank #1657 of 10916 rated models, from 143 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Knowledge - Common Sense - Chinese (CompassBench 2405) | 82 | Score (%) | 100 |
| OpenCompass Knowledge - Natural Science - Chinese (CompassBench 2405) | 63.5 | Score (%) | 100 |
| OpenCompass Knowledge - Social Science - Chinese (CompassBench 2405) | 74.2 | Score (%) | 100 |
| OpenCompass LLM - Knowledge (CompassBench 2405) | 76.6 | Score (%) | 100 |
| OpenCompass LLM - Knowledge - Chinese (CompassBench 2405) | 70.8 | Score (%) | 100 |
| OpenCompass LLM - Language (CompassBench 2407) | 56.5 | Score (%) | 100 |
| OpenCompass LLM - Language - Chinese (CompassBench 2407) | 60.8 | Score (%) | 100 |
| OpenCompass LLM - Language - English (CompassBench 2407) | 52.2 | Score (%) | 100 |
| OpenCompass Language - Creation - Chinese (CompassBench 2407) | 64 | Score (%) | 100 |
| OpenCompass Language - Dialogue - English (CompassBench 2407) | 59.7 | Score (%) | 100 |
| OpenCompass Reasoning - Humanities - Chinese (CompassBench 2407) | 61.1 | Score (%) | 100 |
| OpenCompass Subjective - Creation - Chinese (CompassBench 2405) | 72 | Score (%) | 100 |
Interactive version: theaggregate.ai/model?slug=qwen-max-04-28 · How It Works · Data refreshed daily, snapshot 2026-11-08.