OpsEval / data /network_zh_qa.csv
Junetheriver's picture
added leaderboards
a6d507f
raw
history blame
499 Bytes
name,rouge1,rouge2,rouge_l,rouge_lsum,score,bp,sys_len,gpt4_score
GPT-3.5-turbo,17.28,6.39,16.84,16.87,1.89,0.74,368,6.98
ChatGLM2-6B,6.92,1.97,6.83,6.75,0.11,1,1867,4.46
InternLM-7B,2.76,1.03,2.76,2.76,0.01,1,6053,2.22
Baichuan-13B-Chat,9.09,3.67,9.04,9.2,0.53,1,1125,5.14
LLaMA-2-13B,4.29,1.29,4.2,4.22,0.23,1,1581,5.03
Chinese-LLaMA-2-13B,4.96,4.11,4.7,4.73,0.01,1,11371,1.77
Chinese-Alpaca-2-13B,10.03,2.19,9.86,9.97,0.02,1,2605,4.71
Qwen-7B-Chat,10,2.45,9.94,10.05,0.23,0.42,257,5.07