OpsEval / data_v2 /zjyd_zh_mc_gen.csv
Junetheriver's picture
update 05-15
32e04fa
raw
history blame
1.63 kB
name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_self_con
Baichuan-13B-Chat,11.04,11.13,26.92,28.61,14.35,13.22,31.69,33.97
Chatglm2-6B,23.09,23.12,24.22,24.08,30.46,30.46,35.97,35.9
Chatglm3-6B,32.6,32.6,35.4,35.4,28.3,28.3,40.9,40.9
Chinese-Alpaca-2-13B,22.69,22.69,24.59,24.59,40.52,40.52,40.73,40.73
Chinese-Llama-2-13B,17.98,17.98,17.83,17.83,31.66,31.66,36.24,36.24
Devops-Model-14B-Chat,41.04,42.7,48.71,53.57,56.85,57.25,51.3,54.29
Ernie-Bot-4.0,45.99,45.99,48.98,48.98,46.0,46.0,54.0,54.0
Glm3-Turbo,43.0,43.0,,,,,,
Glm4,50.0,50.0,,,,,,
Gpt-3.5-Turbo,37.06,36.83,37.56,39.25,39.42,39.77,41.96,42.15
Gpt-4,,,57.35,62.11,,,61.2,65.68
Internlm-7B,27.81,27.81,19.95,19.95,24.18,24.18,35.35,35.35
Internlm2-Chat-20B,44.6,44.6,47.0,47.0,62.2,62.2,38.3,38.3
Internlm2-Chat-7B,38.8,38.8,44.6,44.6,46.0,46.0,35.8,35.8
Llama-2-13B,25.43,27.16,29.17,29.99,36.56,36.15,37.7,39.02
Llama-2-70B-Chat,24.38,24.38,43.63,43.63,44.65,44.65,48.84,48.84
Llama-2-7B,24.09,23.47,28.69,29.26,29.94,30.03,31.35,31.93
Mistral-7B,1.27,1.27,42.05,42.05,30.72,30.72,46.44,46.44
Qwen-14B-Chat,41.71,41.44,45.58,47.98,53.52,49.92,54.72,58.85
Qwen-72B-Chat,64.79,64.79,65.79,65.72,70.19,70.19,68.31,68.38
Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
gemma_2b,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
gemma_7b,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
Qwen1.5-14B-Base,49.1,63.425925925925924,49.9,0.0,62.5,66.2037037037037,41.3,25.0
Qwen1.5-14B-Chat,38.6,49.1,48.8,49.9,54.6,62.5,52.1,41.3
Qwen1.5-14B-Chat,,38.9,,50.5,,55.2,,52.7