Qwen1.5-MoE-A2.7B-Chat: benchmark results
Provider: Alibaba. Released 2024-03-14. Access: Open.
Unified ELO 1366 ± 1, rank #1227 of 1392 rated models, from 94 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - CMMLU | 54.31 | Accuracy (%) | 55.8 |
| RewardBench Chat Hard | 63.16 | Accuracy (%) | 55.1 |
| Open Chinese LLM - HellaSwag | 60.57 | Accuracy (%) | 54.3 |
| Open Chinese LLM - WinoGrande | 62.59 | Accuracy (%) | 45.8 |
| Open Chinese LLM - C-Eval Semantic | 67.78 | Accuracy (%) | 44.2 |
| RewardBench | 66.44 | Score (%) | 44.1 |
| RewardBench Reasoning | 77.4 | Accuracy (%) | 42.9 |
| Open LLM Leaderboard - IFEval | 37.95 | Score | 37.2 |
| Open LLM Leaderboard - MATH Level 5 | 6.34 | Score | 34.6 |
| MERA - RWSD | 52.69 | Accuracy (%) | 34.2 |
| Open LLM Leaderboard - MMLU-Pro | 21.37 | Score | 34 |
| MERA - ruDetox | 12.54 | Joint Score (%) | 31 |
Interactive version: theaggregate.ai/model?slug=qwen1-5-moe-a2-7b-chat · How It Works · Data refreshed daily, snapshot 2026-09-05.