name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_self_con
Baichuan2-13B-Chat,41.76,41.76,53.85,60.44,38.46,38.46,49.45,51.65
ChatGLM3-6B,43.95604396,43.95604396,53.84615385,53.84615385,43.95604396,43.95604396,47.25274725,47.25274725
DevOps-Model-14B-Chat,41.76,38.46,45.05,49.45,61.54,59.34,52.75,63.74
ERNIE-Bot-4.0,68.13,68.13,64.84,64.84,65.93,65.93,68.13,68.13
GPT-3.5-turbo,49.45,52.75,59.34,62.64,47.25,52.75,57.14,58.24
GPT-4,68.13,68.13,67.03,67.03,70.33,70.33,71.43,71.43
InternLM2-Chat-20B,56.04395604,56.04395604,,,65.93406593,65.93406593,,
InternLM2-Chat-7B,56.04395604,56.04395604,59.34065934,59.34065934,54.94505495,54.94505495,51.64835165,51.64835165
LLaMA-2-13B,30.77,30.77,47.25,47.25,47.25,47.25,42.86,42.86
LLaMA-2-70B-Chat,6.59,6.59,48.35,48.35,19.78,19.78,49.45,49.45
LLaMA-2-7B,28.57,28.57,45.05,45.05,42.86,42.86,45.05,45.05
Mistral-7B,5.49,5.49,47.25,47.25,14.29,14.29,38.46,38.46
Qwen-14B-Chat,47.25,47.25,53.85,54.95,54.95,54.95,59.34,61.54
Qwen-72B-Chat,71.43,71.43,67.03,67.03,70.33,70.33,74.73,74.73
Yi-34B-Chat,71.43,74.73,71.43,73.63,69.23,70.33,49.45,47.25
Claude-3-Opus,41.508438818565395,41.508438818565395,,,,,,
Deepseek-R1-Distill-Llama-8B,33.38607594936709,33.38607594936709,42.24683544303797,42.24683544303797,38.449367088607595,38.449367088607595,38.71308016877637,38.71308016877637
Deepseek-R1-Distill-Qwen-1.5B,31.11814345991561,31.11814345991561,24.68354430379747,24.68354430379747,22.890295358649787,22.890295358649787,26.951476793248943,26.951476793248943
Deepseek-R1-Distill-Qwen-14B,38.34388185654008,38.34388185654008,,,36.075949367088604,36.075949367088604,,
Deepseek-R1-Distill-Qwen-32B,48.20675105485232,48.20675105485232,,,44.67299578059072,44.67299578059072,,
Deepseek-R1-Distill-Qwen-7B,39.71518987341772,39.71518987341772,29.746835443037973,29.746835443037973,27.584388185654007,27.584388185654007,40.348101265822784,40.348101265822784
Gemma-2B,30.76923,30.76923,43.95604,43.95604,32.96703,32.96703,29.67033,29.67033
Gemma-7B,29.67033,29.67033,56.04396,56.04396,34.06593,34.06593,50.54945,50.54945
Meta-Llama-3-8B-Instruct,36.550632911392405,36.550632911392405,38.08016877637131,38.08016877637131,43.24894514767932,43.24894514767932,34.28270042194093,34.28270042194093
Qwen1.5-14B-Base,53.84615,53.84615,63.73626,63.73626,68.13187,68.13187,42.85714,42.85714
Qwen1.5-14B-Chat,56.04396,54.94505,67.03297,68.13187,59.34066,57.14286,60.43956,62.63736