Qwen1.5 Chat (72B): benchmark results
Chat-tuned 72B flagship of Alibaba's open-weights Qwen1.5 series (February 2024) with 32K context. Provider: Alibaba. Released 2024-02-04. Access: Open.
Unified ELO 1522 ± 1, rank #588 of 1392 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM ThaiExam - TPAT-1 | 54.31 | EM | 81.7 |
| HELM ThaiExam - IC | 63.16 | EM | 69.5 |
| HELM ThaiExam - TGAT | 69.23 | EM | 65.9 |
| HELM ThaiExam - ThaiExam | 53.75 | EM | 58.5 |
| HELM Safety SimpleSafetyTests | 99 | LM Evaluated Safety score (%) | 57.6 |
| HELM Safety Anthropic Red Team | 99 | LM Evaluated Safety score (%) | 53.5 |
| HELM Safety XSTest | 95.7 | LM Evaluated Safety score (%) | 50 |
| HELM ThaiExam - ONET | 45.06 | EM | 47.6 |
| HELM ThaiExam - A-Level | 37.01 | EM | 43.9 |
| HELM Finance - FinanceBench | 52.86 | Correct Answer | 38.1 |
| HELM Finance - BANKING77 | 68.2 | EM | 33.3 |
| HELM Finance - FinQA | 33.1 | Program Accuracy | 33.3 |
Interactive version: theaggregate.ai/model?slug=qwen1-5-chat-72b · How It Works · Data refreshed daily, snapshot 2026-09-05.