Qwen 1.5 110B: benchmark results
Alibaba's first 100B+ open-weights Qwen release (April 2024), a 110B dense base model with GQA and 32K context. Provider: Alibaba. Released 2024-04-25. Access: Open.
Aggregate Rating 1515 ± 18, rank #734 of 1656 rated models, from 104 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 81.05 | Accuracy (%) (5-shot) | 99.8 |
| Open LLM Leaderboard v1 - MMLU | 80.2 | Accuracy (%) (5-shot) | 99.7 |
| Open LLM Leaderboard - MMLU-Pro | 53.61 | Score | 94 |
| HELM MMLU - College Chemistry | 62 | EM | 92.3 |
| Open LLM Leaderboard v1 - WinoGrande | 84.14 | Accuracy (%) (5-shot) | 92.1 |
| HELM MMLU - High School Government And Politics | 98.45 | EM | 91.7 |
| HELM MMLU - High School European History | 88.48 | EM | 89.7 |
| Open LLM Leaderboard - GPQA | 35.23 | Score | 88.6 |
| CMMLU | 88.32 | 5-shot Avg Accuracy (%) | 87.5 |
| Open LLM Leaderboard v1 - HellaSwag | 87.48 | Normalized accuracy (%) (10-shot) | 86.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 69.97 | Normalized accuracy (%) (25-shot) | 84.7 |
| Open LLM Leaderboard - BBH | 61 | Score | 83.8 |
Interactive version: theaggregate.ai/model?slug=qwen-1-5-110b · How It Works · Data refreshed daily, snapshot 2026-10-20.