name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_self_con GPT-4,,,87.07482993197279,87.07482993197279,87.07482993197279,87.07482993197279,91.15646258503402,91.15646258503402 GPT-4o,87.07482993197279,87.07482993197279,89.1156462585034,89.1156462585034,89.1156462585034,89.1156462585034,91.15646258503402,91.15646258503402 Baichuan2-7B-Chat,62.585034013605444,62.585034013605444,,,42.857142857142854,42.857142857142854,, Claude-3-Opus,83.6734693877551,83.6734693877551,85.03401360544217,85.03401360544217,87.75510204081633,87.75510204081633,91.83673469387756,91.83673469387756 Deepseek-R1-Distill-Llama-8B,55.78231292517006,55.78231292517006,76.19047619047619,76.19047619047619,72.10884353741497,72.10884353741497,78.2312925170068,78.2312925170068 Deepseek-R1-Distill-Qwen-1.5B,59.863945578231295,59.863945578231295,58.50340136054422,58.50340136054422,41.49659863945578,41.49659863945578,71.42857142857143,71.42857142857143 Deepseek-R1-Distill-Qwen-14B,68.70748299319727,68.70748299319727,,,72.78911564625851,72.78911564625851,, Deepseek-R1-Distill-Qwen-32B,87.07482993197279,87.07482993197279,,,85.71428571428571,85.71428571428571,, Deepseek-R1-Distill-Qwen-7B,62.585034013605444,62.585034013605444,64.62585034013605,64.62585034013605,57.82312925170068,57.82312925170068,67.3469387755102,67.3469387755102 Qwen2-0.5B-Instruct,56.4625850340136,56.4625850340136,,,,,57.14285714285714,57.14285714285714 Qwen2-1.5B-Instruct,,,68.02721088435374,68.02721088435374,,,, Qwen2-7B-Instruct,76.19047619047619,76.19047619047619,80.95238095238095,80.95238095238095,76.87074829931973,76.87074829931973,,