Qwen 1.5 1.8B Chat: benchmark results
Alibaba's Qwen1.5-1.8B-Chat, the aligned chat version of Qwen1.5-1.8B, post-trained with supervised fine-tuning and direct preference optimization, supporting a 32K context window. Provider: Alibaba. Released 2024-02-04. Access: Open.
Aggregate Rating 1253 ± 14, rank #1537 of 1656 rated models, from 137 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 42.6 | Score | 66.4 |
| Open LLM Leaderboard - GPQA | 29.78 | Score | 53.6 |
| RewardBench Chat Hard | 60.31 | Accuracy (%) | 46.9 |
| RewardBench Reasoning | 77.93 | Accuracy (%) | 45.6 |
| MERA - RWSD | 55 | Accuracy (%) | 43.3 |
| Open LLM Leaderboard v1 - GSM8K | 19.03 | Accuracy (%) (5-shot) | 40.3 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 54.92 | Character F1 (%) | 30.9 |
| EuroEval English Knowledge | 44.42 | Knowledge Average Score (%) | 28.9 |
| Open Portuguese LLM - OAB Exams | 31.71 | Accuracy (%) | 28.6 |
| EuroEval Norwegian Common Sense Reasoning | 15.29 | Common Sense Reasoning Average Score (%) | 28.5 |
| EuroEval Norwegian Knowledge - NRK Quiz QA | 9.28 | MCC (x100) | 27.5 |
| EuroEval Danish Knowledge | 17.4 | Knowledge Average Score (%) | 27.3 |
Interactive version: theaggregate.ai/model?slug=qwen-1-5-1-8b-chat · How It Works · Data refreshed daily, snapshot 2026-10-20.