Question Answering on Expressway Laws & Regulations QA
98.4MCQ AccuracyExpressMind-14B
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| ExpressMind-14BParameters=14B2026.03 | 98.4 | 97.9 | 98.1 | 98.2 | 97.5 | 98.3 | 97.4 | 90.5 | 86.8 | 88.5 | |
| Qwen-32BParameters=32B2026.03 | 97.9 | 96.5 | 97.2 | 96.1 | 95.8 | 96.4 | 93.7 | 85.3 | 75.6 | 82.1 | |
| Llama-3.3-70BParameters=70B2026.03 | 97.5 | 96 | 96.8 | 96.5 | 96.2 | 96.8 | 96.6 | 89.4 | 86.1 | 87.2 | |
| DeepSeek-R1-Distill-Llama-70BParameters=70B, Backbone=Llama2026.03 | 97 | 96.2 | 96.5 | 97 | 95.8 | 96.4 | 95.9 | 88.7 | 85.9 | 87.8 | |
| DeepSeek-R1-Distill-Qwen-32BParameters=32B, Backbone=Qwen2026.03 | 96.1 | 96.3 | 97.4 | 96.5 | 96 | 96.1 | 92.4 | 84.1 | 76.6 | 82.4 | |
| GLM-4-32BParameters=32B2026.03 | 91.7 | 89.4 | 90.5 | 90.1 | 89.5 | 90.3 | 90.4 | 80.5 | 71.4 | 76.4 | |
| Baichuan-32BParameters=32B2026.03 | 91.3 | 88.5 | 89.9 | 89.5 | 88.2 | 89.4 | 88.8 | 78.2 | 69.3 | 74.5 |