Qwen 1.5 14B Chat: benchmark results
Chat-tuned Qwen1.5 14B checkpoint. Provider: Alibaba. Released 2024-02-05. Access: Open.
Unified ELO 1460 ± 1, rank #897 of 1392 rated models, from 206 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenEval - BBQ | 93.49 | Exact Match (%) | 90.9 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 75.98 | Reading comprehension Score (%) | 88.5 |
| Open Korean LLM Leaderboard | 42.59 | Average Score (%) | 83.7 |
| Open Chinese LLM - GSM8K | 59.06 | Accuracy (%) | 82.6 |
| Open Chinese LLM - HellaSwag | 65.16 | Accuracy (%) | 78.6 |
| EuroEval Swedish NLU - Swerec | 77.66 | Sentiment classification Score (%) | 78.2 |
| EuroEval Portuguese NLU - ScaLA PT | 23.99 | Linguistic acceptability Score (%) | 77.5 |
| EuroEval German NLU - Sb10K | 55.97 | Sentiment classification Score (%) | 77.2 |
| Open Chinese LLM Leaderboard | 63.79 | Average Score (%) | 77.2 |
| Open Japanese LLM - Xlsum JA Rouge1 | 29.25 | Score (%) | 76.9 |
| EuroEval Portuguese NLU | 55.66 | NLU Average Score (%) | 76.7 |
| Open LLM Leaderboard - MuSR | 13.93 | Score | 76.5 |
Interactive version: theaggregate.ai/model?slug=qwen-1-5-14b-chat · How It Works · Data refreshed daily, snapshot 2026-09-05.