update leaderboard 2024-09-06

data_v2/inspur_en_mc_gen.csv

@@ -0,0 +1,7 @@
+name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_self_con
+Gpt-4,85.71428571428571,85.71428571428571,87.75510204081633,87.75510204081633,90.47619047619048,90.47619047619048,91.15646258503402,91.15646258503402
+Gpt-4O,89.79591836734694,89.79591836734694,90.47619047619048,90.47619047619048,91.15646258503402,91.15646258503402,92.51700680272108,92.51700680272108
+Baichuan2-7B-Chat,44.89795918367347,44.89795918367347,66.66666666666666,66.66666666666666,28.57142857142857,28.57142857142857,50.34013605442177,50.34013605442177
+Claude-3-Opus,87.75510204081633,87.75510204081633,89.1156462585034,89.1156462585034,91.15646258503402,91.15646258503402,88.43537414965986,88.43537414965986
+Qwen2-0.5B-Instruct,80.95238095238095,80.95238095238095,53.06122448979592,53.06122448979592,65.98639455782312,65.98639455782312,52.38095238095239,52.38095238095239
+Qwen2-7B-Instruct,,,67.3469387755102,67.3469387755102,80.27210884353741,80.27210884353741,82.31292517006803,82.31292517006803

data_v2/inspur_zh_mc_gen.csv

@@ -0,0 +1,6 @@
+name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_self_con
+Gpt-4,87.07482993197279,87.07482993197279,87.07482993197279,87.07482993197279,87.07482993197279,87.07482993197279,91.15646258503402,91.15646258503402
+Gpt-4O,62.585034013605444,62.585034013605444,89.1156462585034,89.1156462585034,89.1156462585034,89.1156462585034,91.15646258503402,91.15646258503402
+Claude-3-Opus,83.6734693877551,83.6734693877551,85.03401360544217,85.03401360544217,42.857142857142854,42.857142857142854,91.83673469387756,91.83673469387756
+Qwen2-0.5B-Instruct,56.4625850340136,56.4625850340136,68.02721088435374,68.02721088435374,87.75510204081633,87.75510204081633,57.14285714285714,57.14285714285714
+Qwen2-7B-Instruct,76.19047619047619,76.19047619047619,80.95238095238095,80.95238095238095,76.87074829931973,76.87074829931973,,