OpsEval / data_v2 /network_zh_mc_gen.csv
Junetheriver's picture
update 05-15
32e04fa
raw
history blame
No virus
2.03 kB
name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_self_con
Aquilachat2-34B,34.66,34.66,47.74,47.74,44.48,44.48,,
Baichuan-13B-Chat,15.2,16.0,43.9,49.7,34.3,36.1,51.3,55.6
Baichuan2-13B-Chat,35.6,35.9,30.5,30.5,34.6,35.6,30.2,32.0
Chatglm2-6B,33.8,33.7,42.1,42.2,36.0,36.0,39.5,39.5
Chatglm3-6B,41.39414802,41.39414802,49.22547332,49.22547332,38.81239243,38.81239243,42.85714286,42.85714286
Chinese-Alpaca-2-13B,33.1,33.1,44.2,44.2,44.0,44.0,42.7,42.7
Chinese-Llama-2-13B,22.5,22.5,38.8,38.8,41.8,41.8,32.2,32.2
Devops-Model-14B-Chat,47.59,46.57,52.52,56.01,62.07,60.08,50.59,55.79
Ernie-Bot-4.0,67.54,67.54,71.96,71.96,72.0,72.0,78.0,78.0
Glm3-Turbo,59.63855422,59.63855422,,,,,,
Glm4,67.383821,67.383821,,,,,,
Gpt-3.5-Turbo,58.4,58.6,64.8,67.6,59.2,59.7,65.2,67.4
Gpt-4,,,,,,,86.0,86.0
Hunyuan-13B,60.0,60.0,70.0,70.0,,,,
Internlm-7B,41.7,41.7,38.4,38.4,42.6,42.6,41.3,41.3
Internlm2-Chat-20B,57.48709122,57.48709122,57.14285714,57.14285714,59.1222031,59.1222031,50.77452668,50.77452668
Internlm2-Chat-7B,54.30292599,54.30292599,59.81067126,59.81067126,58.51979346,58.51979346,51.63511188,51.63511188
Llama-2-13B,29.7,31.6,51.6,57.0,39.6,38.9,48.0,50.6
Llama-2-70B-Chat,38.55,38.55,57.49,57.49,49.09,49.09,48.57,48.57
Llama-2-7B,29.8,30.2,50.1,55.6,38.6,40.8,45.6,50.4
Mistral-7B,1.9,1.9,45.61,45.61,15.0,15.0,35.97,35.97
Qwen-14B-Chat,48.35,48.81,55.35,57.4,58.53,56.12,52.12,54.99
Qwen-72B-Chat,65.77,65.86,68.13,68.3,69.4,69.4,69.99,70.08
Qwen-7B-Chat,29.6,29.9,50.6,53.5,50.4,46.9,46.9,47.7
Yi-34B-Chat,61.61,62.56,68.11,69.75,65.73,65.37,69.88,71.21
gemma_2b,29.69019,29.69019,39.15663,39.15663,29.77625,29.77625,38.64028,38.64028
gemma_7b,31.58348,31.58348,47.59036,47.59036,34.68158,34.68158,48.88124,48.88124
Qwen1.5-14B-Base,45.18072,35.904696806952444,59.1222,38.94801939914722,61.10155,41.717931191615406,52.4957,31.059792337987826
Qwen1.5-14B-Chat,54.04475,45.18072,62.56454,59.1222,58.77797,61.10155,63.42513,52.4957
Qwen1.5-14B-Chat,,53.87263,,63.85542,,58.0895,,65.57659