XuanYuan-70B: benchmark results
Du Xiaoman's Chinese financial LLM, a continued pretrain of Llama 2 70B on Chinese and finance corpora with context extended to 8k/16k (September 2023). Provider: Du Xiaoman. Released 2023-09-22. Access: Open.
Aggregate Rating 1530 ± 43, rank #1947 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Chinese LLM - WinoGrande | 68.27 | Accuracy (%) | 86.5 |
| Open Chinese LLM - HellaSwag | 68.09 | Accuracy (%) | 86.4 |
| Open Chinese LLM - ARC Challenge | 59.39 | Accuracy (%) | 84.2 |
| Open Chinese LLM - C-Eval Semantic | 86.68 | Accuracy (%) | 81.1 |
| Open Chinese LLM Leaderboard | 64.23 | Official Nonzero-Task Mean (%) | 79.3 |
| Open Chinese LLM - CMMLU | 63.99 | Accuracy (%) | 75.3 |
| Open Chinese LLM - GSM8K | 51.63 | Accuracy (%) | 70.4 |
| C-Eval | 71.9 | Average (%) | 62 |
| CMMLU | 71.1 | 5-shot Avg Accuracy (%) | 55 |
| Open Chinese LLM - TruthfulQA MC | 51.53 | Accuracy (%) | 29 |
Interactive version: theaggregate.ai/model?slug=xuanyuan-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.