update leaderboard 2025-08-14

data_v2/bosc_zh_mc_gen.csv

@@ -14,14 +14,14 @@ Mistral-7B,0.0,0.0,37.5,37.5,20.0,20.0,50.0,50.0
 Qwen-14B-Chat,47.5,45.0,50.0,47.5,50.0,47.5,55.0,57.5
 Qwen-72B-Chat,50.0,50.0,47.5,47.5,45.0,45.0,60.0,60.0
 Yi-34B-Chat,55.0,55.0,60.0,67.5,50.0,50.0,52.5,55.0
-Claude-3-Opus,72.85714285714286,72.85714285714286,,,,,,
 Deepseek-R1-Distill-Llama-8B,51.42857142857143,51.42857142857143,48.57142857142857,48.57142857142857,50.0,50.0,41.42857142857143,41.42857142857143
 Deepseek-R1-Distill-Qwen-1.5B,42.857142857142854,42.857142857142854,45.71428571428571,45.71428571428571,34.285714285714285,34.285714285714285,34.285714285714285,34.285714285714285
-Deepseek-R1-Distill-Qwen-14B,50.0,50.0,,,51.42857142857143,51.42857142857143,,
-Deepseek-R1-Distill-Qwen-32B,77.14285714285714,77.14285714285714,,,64.28571428571428,64.28571428571428,,
 Deepseek-R1-Distill-Qwen-7B,35.71428571428571,35.71428571428571,41.42857142857143,41.42857142857143,50.0,50.0,22.857142857142858,22.857142857142858
 Gemma-2B,37.5,37.5,40.0,40.0,32.5,32.5,40.0,40.0
 Gemma-7B,32.5,32.5,62.5,62.5,40.0,40.0,50.0,50.0
 Meta-Llama-3-8B-Instruct,52.85714285714286,52.85714285714286,47.14285714285714,47.14285714285714,52.85714285714286,52.85714285714286,30.0,30.0
 Qwen1.5-14B-Base,47.5,47.5,50.0,50.0,47.5,47.5,45.0,45.0
 Qwen1.5-14B-Chat,45.0,47.5,60.0,72.5,52.5,55.0,60.0,60.0
+Deepseek-R1-Distill-Qwen-14B,50.0,50.0,,,51.42857142857143,51.42857142857143,,
+Deepseek-R1-Distill-Qwen-32B,77.14285714285714,77.14285714285714,,,64.28571428571428,64.28571428571428,,
+Claude-3-Opus,72.85714285714286,72.85714285714286,,,,,,

data_v2/gtja_zh_mc_gen.csv

@@ -14,14 +14,14 @@ 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
+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,,
+Claude-3-Opus,41.508438818565395,41.508438818565395,,,,,,

data_v2/huaweicloud_en_mc_gen.csv

@@ -2,8 +2,6 @@ name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,
 GPT-3.5-turbo,40.0,40.0,,,55.00000000000001,55.00000000000001,,
 GPT-4,40.0,40.0,,,55.00000000000001,55.00000000000001,,
 JIUTIAN-75B-net,75.0,75.0,70.0,70.0,80.0,80.0,70.0,70.0
-JIUTIAN-75B-net,45.0,45.0,60.0,60.0,60.0,60.0,70.0,70.0
-Chmobile2026,20.0,20.0,70.0,70.0,15.0,15.0,70.0,70.0
 Deepseek-R1-Distill-Llama-8B,7.5,7.5,32.5,32.5,22.5,22.5,27.5,27.5
 Deepseek-R1-Distill-Qwen-1.5B,10.0,10.0,12.5,12.5,12.5,12.5,22.5,22.5
 Deepseek-R1-Distill-Qwen-14B,27.5,27.5,,,25.0,25.0,,

data_v2/huaweicloud_zh_mc_gen.csv

@@ -7,7 +7,7 @@ GPT-3.5-turbo,13.33,13.33,20.0,26.67,20.0,20.0,16.67,23.33
 GPT-4,20.0,20.0,20.0,20.0,43.33,43.33,46.67,46.67
 InternLM2-Chat-20B,13.33333333,13.33333333,20.0,20.0,16.66666667,16.66666667,,
 InternLM2-Chat-7B,43.33333333,43.33333333,23.33333333,23.33333333,30.0,30.0,40.0,40.0
-JIUTIAN-75B-net,35.0,35.0,65.0,65.0,15.0,15.0,85.0,85.0
+JIUTIAN-75B-net,85.0,85.0,65.0,65.0,75.0,75.0,85.0,85.0
 LLaMA-2-13B,10.0,10.0,20.0,20.0,26.67,26.67,13.33,13.33
 LLaMA-2-70B-Chat,3.33,3.33,20.0,20.0,23.33,23.33,16.67,16.67
 LLaMA-2-7B,10.0,10.0,26.67,26.67,16.67,16.67,33.33,33.33
@@ -15,16 +15,14 @@ Mistral-7B,0.0,0.0,23.33,23.33,0.0,0.0,16.67,16.67
 Qwen-14B-Chat,13.33,13.33,20.0,26.67,40.0,30.0,26.67,33.33
 Qwen-72B-Chat,36.67,36.67,33.33,33.33,43.33,43.33,33.33,36.67
 Yi-34B-Chat,36.67,40.0,36.67,30.0,50.0,46.67,30.0,43.33
-JIUTIAN-75B-net,65.0,65.0,70.0,70.0,50.0,50.0,75.0,75.0
-Chmobile2026,35.0,35.0,65.0,65.0,15.0,15.0,85.0,85.0
-Claude-3-Opus,55.0,55.0,,,,,,
 Deepseek-R1-Distill-Llama-8B,10.0,10.0,30.0,30.0,35.0,35.0,27.5,27.5
 Deepseek-R1-Distill-Qwen-1.5B,25.0,25.0,5.0,5.0,32.5,32.5,20.0,20.0
-Deepseek-R1-Distill-Qwen-14B,50.0,50.0,,,60.0,60.0,,
-Deepseek-R1-Distill-Qwen-32B,60.0,60.0,,,62.5,62.5,,
 Deepseek-R1-Distill-Qwen-7B,10.0,10.0,22.5,22.5,35.0,35.0,32.5,32.5
 Gemma-2B,26.66667,26.66667,10.0,10.0,26.66667,26.66667,20.0,20.0
 Gemma-7B,3.333333,3.333333,23.33333,23.33333,13.33333,13.33333,30.0,30.0
 Meta-Llama-3-8B-Instruct,27.5,27.5,22.5,22.5,30.0,30.0,30.0,30.0
 Qwen1.5-14B-Base,20.0,20.0,33.33333,33.33333,20.0,20.0,30.0,30.0
 Qwen1.5-14B-Chat,23.33333,26.66667,13.33333,13.33333,26.66667,26.66667,20.0,30.0
+Deepseek-R1-Distill-Qwen-14B,50.0,50.0,,,60.0,60.0,,
+Deepseek-R1-Distill-Qwen-32B,60.0,60.0,,,62.5,62.5,,
+Claude-3-Opus,55.0,55.0,,,,,,

data_v2/inspur_en_mc_gen.csv

@@ -5,9 +5,9 @@ Baichuan2-7B-Chat,44.89795918367347,44.89795918367347,66.66666666666666,66.66666
 Claude-3-Opus,87.75510204081633,87.75510204081633,89.1156462585034,89.1156462585034,91.15646258503402,91.15646258503402,88.43537414965986,88.43537414965986
 Deepseek-R1-Distill-Llama-8B,36.054421768707485,36.054421768707485,70.74829931972789,70.74829931972789,34.01360544217687,34.01360544217687,59.863945578231295,59.863945578231295
 Deepseek-R1-Distill-Qwen-1.5B,41.49659863945578,41.49659863945578,50.34013605442177,50.34013605442177,42.17687074829932,42.17687074829932,56.4625850340136,56.4625850340136
-Deepseek-R1-Distill-Qwen-14B,68.02721088435374,68.02721088435374,,,61.904761904761905,61.904761904761905,,
-Deepseek-R1-Distill-Qwen-32B,85.03401360544217,85.03401360544217,,,58.50340136054422,58.50340136054422,,
 Deepseek-R1-Distill-Qwen-7B,42.17687074829932,42.17687074829932,56.4625850340136,56.4625850340136,44.89795918367347,44.89795918367347,74.14965986394559,74.14965986394559
 Qwen2-0.5B-Instruct,,,53.06122448979592,53.06122448979592,,,52.38095238095239,52.38095238095239
-Qwen2-1.5B-Instruct,,,67.3469387755102,67.3469387755102,65.98639455782312,65.98639455782312,,
 Qwen2-7B-Instruct,80.95238095238095,80.95238095238095,,,80.27210884353741,80.27210884353741,82.31292517006803,82.31292517006803
+Deepseek-R1-Distill-Qwen-14B,68.02721088435374,68.02721088435374,,,61.904761904761905,61.904761904761905,,
+Deepseek-R1-Distill-Qwen-32B,85.03401360544217,85.03401360544217,,,58.50340136054422,58.50340136054422,,
+Qwen2-1.5B-Instruct,,,67.3469387755102,67.3469387755102,65.98639455782312,65.98639455782312,,

data_v2/inspur_zh_mc_gen.csv

@@ -1,13 +1,13 @@
 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,,,,
+Baichuan2-7B-Chat,62.585034013605444,62.585034013605444,,,42.857142857142854,42.857142857142854,,
+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,,
 Qwen2-7B-Instruct,76.19047619047619,76.19047619047619,80.95238095238095,80.95238095238095,76.87074829931973,76.87074829931973,,
+Qwen2-1.5B-Instruct,,,68.02721088435374,68.02721088435374,,,,

data_v2/lenovo_en_mc_gen.csv

@@ -4,10 +4,10 @@ InternLM2-Chat-20B,62.5,62.5,,,75.0,75.0,,
 InternLM2-Chat-7B,65.0,65.0,67.5,67.5,75.0,75.0,57.5,57.5
 Deepseek-R1-Distill-Llama-8B,30.0,30.0,60.0,60.0,12.857142857142856,12.857142857142856,47.14285714285714,47.14285714285714
 Deepseek-R1-Distill-Qwen-1.5B,28.571428571428573,28.571428571428573,42.85714285714286,42.85714285714286,31.428571428571427,31.428571428571427,35.71428571428571,35.71428571428571
-Deepseek-R1-Distill-Qwen-14B,47.14285714285714,47.14285714285714,,,32.85714285714286,32.85714285714286,,
-Deepseek-R1-Distill-Qwen-32B,64.28571428571428,64.28571428571428,,,54.285714285714285,54.285714285714285,,
 Deepseek-R1-Distill-Qwen-7B,25.71428571428571,25.71428571428571,37.142857142857146,37.142857142857146,37.14285714285714,37.14285714285714,58.57142857142858,58.57142857142858
 Gemma-2B,22.5,22.5,47.5,47.5,30.0,30.0,37.5,37.5
 Gemma-7B,32.5,32.5,65.0,65.0,35.0,35.0,65.0,65.0
 Qwen1.5-14B-Base,67.5,67.5,70.0,70.0,72.5,72.5,50.0,50.0
 Qwen1.5-14B-Chat,67.5,67.5,70.0,70.0,72.5,65.0,77.5,77.5
+Deepseek-R1-Distill-Qwen-14B,47.14285714285714,47.14285714285714,,,32.85714285714286,32.85714285714286,,
+Deepseek-R1-Distill-Qwen-32B,64.28571428571428,64.28571428571428,,,54.285714285714285,54.285714285714285,,

data_v2/lenovo_zh_mc_gen.csv

@@ -12,10 +12,10 @@ Mistral-7B,47.5,47.5,62.5,62.5,35.0,35.0,60.0,60.0
 Qwen-14B-Chat,70.0,67.5,70.0,67.5,70.0,65.0,65.0,67.5
 Qwen-72B-Chat,72.5,72.5,75.0,75.0,75.0,75.0,75.0,75.0
 Yi-34B-Chat,75.0,75.0,87.5,82.5,62.5,57.5,52.5,52.5
-Claude-3-Opus,71.42857142857143,71.42857142857143,,,,,,
 Deepseek-R1-Distill-Llama-8B,47.142857142857146,47.142857142857146,60.0,60.0,60.0,60.0,40.0,40.0
 Deepseek-R1-Distill-Qwen-1.5B,24.285714285714285,24.285714285714285,34.285714285714285,34.285714285714285,55.71428571428571,55.71428571428571,52.857142857142854,52.857142857142854
-Deepseek-R1-Distill-Qwen-14B,68.57142857142858,68.57142857142858,,,68.57142857142858,68.57142857142858,,
-Deepseek-R1-Distill-Qwen-32B,61.42857142857143,61.42857142857143,,,60.0,60.0,,
 Deepseek-R1-Distill-Qwen-7B,40.0,40.0,30.0,30.0,42.85714285714286,42.85714285714286,57.142857142857146,57.142857142857146
 Meta-Llama-3-8B-Instruct,47.14285714285714,47.14285714285714,44.285714285714285,44.285714285714285,45.714285714285715,45.714285714285715,32.857142857142854,32.857142857142854
+Deepseek-R1-Distill-Qwen-14B,68.57142857142858,68.57142857142858,,,68.57142857142858,68.57142857142858,,
+Deepseek-R1-Distill-Qwen-32B,61.42857142857143,61.42857142857143,,,60.0,60.0,,
+Claude-3-Opus,71.42857142857143,71.42857142857143,,,,,,

data_v2/network_en_mc_gen.csv

@@ -22,16 +22,14 @@ Qwen-14B-Chat,43.78,47.81,56.58,59.4,62.09,59.7,49.06,55.88
 Qwen-72B-Chat,70.41,70.5,72.38,72.56,70.32,70.32,70.13,70.22
 Qwen-7B-Chat,45.9,46.0,47.3,50.1,52.1,51.0,48.3,49.8
 Yi-34B-Chat,57.75,59.14,65.11,68.79,68.16,68.37,78.09,80.06
-JIUTIAN-75B-net,69.38775510204081,69.38775510204081,76.04726100966703,76.04726100966703,72.71750805585391,72.71750805585391,76.1546723952739,76.1546723952739
-Chmobile2026,35.87540279269603,35.87540279269603,74.54350161117078,74.54350161117078,21.804511278195488,21.804511278195488,74.22126745435015,74.22126745435015
-Claude-3-Opus,69.03417341637355,69.03417341637355,,,,,,
 Deepseek-R1-Distill-Llama-8B,19.65121264227399,19.65121264227399,44.240352567500906,44.240352567500906,25.932243238384128,25.932243238384128,37.26068697187482,37.26068697187482
 Deepseek-R1-Distill-Qwen-1.5B,15.894119111389756,15.894119111389756,20.67346477782439,20.67346477782439,18.523623589937444,18.523623589937444,25.022012419153338,25.022012419153338
-Deepseek-R1-Distill-Qwen-14B,37.09841741078631,37.09841741078631,,,31.725773661621865,31.725773661621865,,
-Deepseek-R1-Distill-Qwen-32B,61.682486412229224,61.682486412229224,,,37.41811610571493,37.41811610571493,,
 Deepseek-R1-Distill-Qwen-7B,17.8256800800284,17.8256800800284,35.38237070296834,35.38237070296834,25.341711114081956,25.341711114081956,34.738132885862726,34.738132885862726
 Gemma-2B,26.46048,26.46048,33.41924,33.41924,26.6323,26.6323,37.54296,37.54296
 Gemma-7B,25.08591,25.08591,50.85911,50.85911,30.24055,30.24055,51.55747,51.55747
 Meta-Llama-3-8B-Instruct,38.279481659390655,38.279481659390655,76.69172932330827,76.69172932330827,23.734458771084668,23.734458771084668,33.241749376506874,33.241749376506874
 Qwen1.5-14B-Base,34.87973,34.87973,60.82474,60.82474,65.54983,65.54983,47.07904,47.07904
 Qwen1.5-14B-Chat,54.89691,56.4433,64.08935,67.09622,52.23368,53.52234,59.53608,64.17526
+Deepseek-R1-Distill-Qwen-14B,37.09841741078631,37.09841741078631,,,31.725773661621865,31.725773661621865,,
+Deepseek-R1-Distill-Qwen-32B,61.682486412229224,61.682486412229224,,,37.41811610571493,37.41811610571493,,
+Claude-3-Opus,69.03417341637355,69.03417341637355,,,,,,

data_v2/network_zh_mc_gen.csv

@@ -16,7 +16,7 @@ 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
-JIUTIAN-75B-net,48.442534908700324,48.442534908700324,74.11385606874329,74.11385606874329,33.941997851772285,33.941997851772285,81.41783029001074,81.41783029001074
+JIUTIAN-75B-net,71.75080558539206,71.75080558539206,74.11385606874329,74.11385606874329,69.70998925886144,69.70998925886144,81.41783029001074,81.41783029001074
 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
@@ -25,16 +25,14 @@ 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
-JIUTIAN-75B-net,66.38023630504833,66.38023630504833,74.75832438238453,74.75832438238453,67.88399570354457,67.88399570354457,74.43609022556392,74.43609022556392
-Chmobile2026,48.442534908700324,48.442534908700324,74.11385606874329,74.11385606874329,33.941997851772285,33.941997851772285,81.41783029001074,81.41783029001074
-Claude-3-Opus,62.329525111479995,62.329525111479995,,,,,,
 Deepseek-R1-Distill-Llama-8B,27.380138658334147,27.380138658334147,41.48846141327344,41.48846141327344,32.6123750935781,32.6123750935781,33.60348924258699,33.60348924258699
 Deepseek-R1-Distill-Qwen-1.5B,24.732285258601046,24.732285258601046,24.071542492595125,24.071542492595125,20.06151742993848,20.06151742993848,25.47277284119389,25.47277284119389
-Deepseek-R1-Distill-Qwen-14B,45.859779318425936,45.859779318425936,,,47.220323536113014,47.220323536113014,,
-Deepseek-R1-Distill-Qwen-32B,58.3829704130456,58.3829704130456,,,57.567620349575236,57.567620349575236,,
 Deepseek-R1-Distill-Qwen-7B,30.83520489535527,30.83520489535527,31.99882823942974,31.99882823942974,26.802395599388078,26.802395599388078,33.14454968590307,33.14454968590307
 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
 Meta-Llama-3-8B-Instruct,35.904696806952444,35.904696806952444,38.94801939914722,38.94801939914722,41.717931191615406,41.717931191615406,31.059792337987826,31.059792337987826
 Qwen1.5-14B-Base,45.18072,45.18072,59.1222,59.1222,61.10155,61.10155,52.4957,52.4957
 Qwen1.5-14B-Chat,54.04475,53.87263,62.56454,63.85542,58.77797,58.0895,63.42513,65.57659
+Deepseek-R1-Distill-Qwen-14B,45.859779318425936,45.859779318425936,,,47.220323536113014,47.220323536113014,,
+Deepseek-R1-Distill-Qwen-32B,58.3829704130456,58.3829704130456,,,57.567620349575236,57.567620349575236,,
+Claude-3-Opus,62.329525111479995,62.329525111479995,,,,,,

data_v2/oracle_en_mc_gen.csv

@@ -22,15 +22,14 @@ Qwen-14B-Chat,24.95,28.37,33.0,36.62,27.97,28.37,27.97,24.14
 Qwen-72B-Chat,47.28,47.48,48.09,48.09,49.7,49.7,43.46,43.66
 Qwen-7B-Chat,18.91,19.11,22.13,23.94,26.76,25.55,34.81,33.4
 Yi-34B-Chat,47.08,48.69,47.08,46.28,58.15,58.35,56.94,58.95
-Chmobile2026,50.877192982456144,50.877192982456144,72.36842105263158,72.36842105263158,36.40350877192983,36.40350877192983,68.85964912280701,68.85964912280701
-Claude-3-Opus,48.31816996021653,48.31816996021653,,,,,,
 Deepseek-R1-Distill-Llama-8B,13.362518750407617,13.362518750407617,31.26345137937781,31.26345137937781,23.33528989760647,23.33528989760647,32.98441270462401,32.98441270462401
 Deepseek-R1-Distill-Qwen-1.5B,15.083480075653819,15.083480075653819,18.153655514250307,18.153655514250307,16.92346572751582,16.92346572751582,24.784777929955,24.784777929955
-Deepseek-R1-Distill-Qwen-14B,31.89199765212287,31.89199765212287,,,36.61628513663341,36.61628513663341,,
-Deepseek-R1-Distill-Qwen-32B,50.49240200873932,50.49240200873932,,,40.329681080023484,40.329681080023484,,
 Deepseek-R1-Distill-Qwen-7B,15.674525533163767,15.674525533163767,29.412867671036324,29.412867671036324,19.859942607447987,19.859942607447987,27.435107284940976,27.435107284940976
 Gemma-2B,16.90141,16.90141,19.5171,19.5171,16.09658,16.09658,24.74849,24.74849
 Gemma-7B,14.28571,14.28571,30.98592,30.98592,2.60223,2.60223,43.85965,43.85965
 Meta-Llama-3-8B-Instruct,28.468825409248026,28.468825409248026,40.47805387073632,40.47805387073632,23.33528989760647,23.33528989760647,34.6197743429205,34.6197743429205
 Qwen1.5-14B-Base,29.17505,29.17505,33.60161,33.60161,36.82093,36.82093,27.7666,27.7666
 Qwen1.5-14B-Chat,32.79678,35.41247,39.43662,43.05835,32.39437,33.60161,36.82093,38.833
+Deepseek-R1-Distill-Qwen-14B,31.89199765212287,31.89199765212287,,,36.61628513663341,36.61628513663341,,
+Deepseek-R1-Distill-Qwen-32B,50.49240200873932,50.49240200873932,,,40.329681080023484,40.329681080023484,,
+Claude-3-Opus,48.31816996021653,48.31816996021653,,,,,,

data_v2/oracle_zh_mc_gen.csv

@@ -12,7 +12,7 @@ GPT-3.5-turbo,36.42,35.81,39.24,43.26,39.84,39.44,27.16,27.77
 GPT-4,,,59.38,65.17,,,44.06,48.09
 InternLM-7B,25.96,25.96,25.96,25.96,29.18,29.18,28.37,28.37
 InternLM2-Chat-7B,28.57142857,28.57142857,31.79074447,31.79074447,30.78470825,30.78470825,31.18712274,31.18712274
-JIUTIAN-75B-net,49.56140350877193,49.56140350877193,70.17543859649122,70.17543859649122,43.42105263157895,43.42105263157895,82.01754385964912,82.01754385964912
+JIUTIAN-75B-net,73.68421052631578,73.68421052631578,70.17543859649122,70.17543859649122,36.84210526315789,36.84210526315789,82.01754385964912,82.01754385964912
 LLaMA-2-13B,23.94,24.35,29.58,31.99,24.55,26.76,21.13,20.72
 LLaMA-2-70B-Chat,15.29,15.29,34.81,34.81,26.76,26.76,33.8,33.8
 LLaMA-2-7B,20.72,20.72,27.16,27.97,21.53,18.51,18.31,17.91
@@ -21,12 +21,8 @@ Qwen-14B-Chat,27.57,27.57,32.39,36.02,40.04,35.41,30.38,33.4
 Qwen-72B-Chat,48.29,48.49,49.5,49.7,49.7,49.7,45.27,44.87
 Qwen-7B-Chat,18.51,17.71,27.36,28.37,29.78,29.58,33.6,31.79
 Yi-34B-Chat,49.9,49.3,52.72,53.72,56.34,56.34,51.31,54.33
-Chmobile2026,49.56140350877193,49.56140350877193,70.17543859649122,70.17543859649122,43.42105263157895,43.42105263157895,82.01754385964912,82.01754385964912
-Claude-3-Opus,50.00570664579664,50.00570664579664,,,,,,
 Deepseek-R1-Distill-Llama-8B,25.90001956564273,25.90001956564273,34.199928259309985,34.199928259309985,29.46096654275093,29.46096654275093,31.583023543990087,31.583023543990087
 Deepseek-R1-Distill-Qwen-1.5B,25.54294658579534,25.54294658579534,21.57682775712516,21.57682775712516,20.87083414856845,20.87083414856845,25.67664514445966,25.67664514445966
-Deepseek-R1-Distill-Qwen-14B,43.671329811517644,43.671329811517644,,,43.575132068088436,43.575132068088436,,
-Deepseek-R1-Distill-Qwen-32B,51.3027457118633,51.3027457118633,,,53.48105393595513,53.48105393595513,,
 Deepseek-R1-Distill-Qwen-7B,26.35736646448836,26.35736646448836,27.31608295832518,27.31608295832518,29.617491684601838,29.617491684601838,31.11100241309594,31.11100241309594
 Gemma-2B,18.51107,18.51107,24.9497,24.9497,21.52918,21.52918,27.7666,27.7666
 Gemma-7B,19.3159,19.3159,53.94737,53.94737,18.51107,18.51107,5.204461,5.204461
@@ -34,3 +30,6 @@ Hisense,42.6270136307311,43.645733955881,43.228657144720536,45.1016345740917,37.
 Meta-Llama-3-8B-Instruct,33.91785690993282,33.91785690993282,27.773429857170807,27.773429857170807,41.359323028761494,41.359323028761494,32.62733972477663,32.62733972477663
 Qwen1.5-14B-Base,20.92555,20.92555,35.61368,35.61368,41.44869,41.44869,30.78471,30.78471
 Qwen1.5-14B-Chat,24.14487,23.34004,40.64386,41.04628,38.22938,38.02817,39.43662,40.04024
+Deepseek-R1-Distill-Qwen-14B,43.671329811517644,43.671329811517644,,,43.575132068088436,43.575132068088436,,
+Deepseek-R1-Distill-Qwen-32B,51.3027457118633,51.3027457118633,,,53.48105393595513,53.48105393595513,,
+Claude-3-Opus,50.00570664579664,50.00570664579664,,,,,,

data_v2/pufa_zh_mc_gen.csv

@@ -14,11 +14,8 @@ Mistral-7B,4.0,4.0,58.67,58.67,22.67,22.67,54.67,54.67
 Qwen-14B-Chat,73.33,73.33,69.33,72.0,73.33,73.33,72.0,80.0
 Qwen-72B-Chat,90.67,90.67,85.33,85.33,88.0,88.0,82.67,82.67
 Yi-34B-Chat,84.0,84.0,88.0,88.0,90.67,92.0,78.67,89.33
-Claude-3-Opus,93.24324324324324,93.24324324324324,,,,,,
 Deepseek-R1-Distill-Llama-8B,24.324324324324326,24.324324324324326,35.13513513513514,35.13513513513514,79.05405405405405,79.05405405405405,26.351351351351347,26.351351351351347
 Deepseek-R1-Distill-Qwen-1.5B,25.0,25.0,22.972972972972975,22.972972972972975,13.513513513513514,13.513513513513514,25.0,25.0
-Deepseek-R1-Distill-Qwen-14B,92.56756756756756,92.56756756756756,,,87.16216216216216,87.16216216216216,,
-Deepseek-R1-Distill-Qwen-32B,95.94594594594595,95.94594594594595,,,95.27027027027026,95.27027027027026,,
 Deepseek-R1-Distill-Qwen-7B,77.70270270270271,77.70270270270271,81.75675675675676,81.75675675675676,26.351351351351347,26.351351351351347,34.45945945945946,34.45945945945946
 Gemma-2B,36.0,36.0,41.33333,41.33333,36.0,36.0,30.66667,30.66667
 Gemma-7B,34.66667,34.66667,56.0,56.0,46.66667,46.66667,56.0,56.0
@@ -26,3 +23,6 @@ Hisense,92.56756756756756,93.36486486468645,93.91891891891892,94.2410479339064,9
 Meta-Llama-3-8B-Instruct,85.8108108108108,85.8108108108108,31.756756756756754,31.756756756756754,83.1081081081081,83.1081081081081,27.7027027027027,27.7027027027027
 Qwen1.5-14B-Base,78.66667,78.66667,72.0,72.0,92.0,92.0,42.66667,42.66667
 Qwen1.5-14B-Chat,86.66667,89.33333,85.33333,85.33333,78.66667,80.0,86.66667,85.33333
+Deepseek-R1-Distill-Qwen-14B,92.56756756756756,92.56756756756756,,,87.16216216216216,87.16216216216216,,
+Deepseek-R1-Distill-Qwen-32B,95.94594594594595,95.94594594594595,,,95.27027027027026,95.27027027027026,,
+Claude-3-Opus,93.24324324324324,93.24324324324324,,,,,,

data_v2/rzy_zh_mc_gen.csv

@@ -14,14 +14,14 @@ Mistral-7B,18.53,18.53,60.3,60.3,29.88,29.88,59.75,59.75
 Qwen-14B-Chat,61.96,61.55,61.55,64.45,65.28,63.49,62.93,65.98
 Qwen-72B-Chat,66.67,66.67,65.28,65.28,65.98,65.98,70.12,70.12
 Yi-34B-Chat,64.45,64.59,67.77,67.36,60.17,60.03,57.68,57.54
-Claude-3-Opus,67.64288271089369,67.64288271089369,,,,,,
 Deepseek-R1-Distill-Llama-8B,40.965278606371555,40.965278606371555,51.60422383963728,51.60422383963728,44.682615439685,44.682615439685,40.891898341486694,40.891898341486694
 Deepseek-R1-Distill-Qwen-1.5B,37.342799188640974,37.342799188640974,35.109175516048204,35.109175516048204,32.75086505190311,32.75086505190311,37.609473809807895,37.609473809807895
-Deepseek-R1-Distill-Qwen-14B,60.99749433241857,60.99749433241857,,,58.225748717336835,58.225748717336835,,
-Deepseek-R1-Distill-Qwen-32B,69.02696575587639,69.02696575587639,,,67.8988187567116,67.8988187567116,,
 Deepseek-R1-Distill-Qwen-7B,53.8294952869586,53.8294952869586,46.16036272521179,46.16036272521179,47.17217515809569,47.17217515809569,47.62379191027324,47.62379191027324
 Gemma-2B,36.37621,36.37621,45.22822,45.22822,33.60996,33.60996,37.75934,37.75934
 Gemma-7B,39.41909,39.41909,54.77178,54.77178,42.04703,42.04703,56.70816,56.70816
 Meta-Llama-3-8B-Instruct,36.55172413793103,36.55172413793103,28.27586206896552,28.27586206896552,38.62068965517241,38.62068965517241,34.48275862068966,34.48275862068966
 Qwen1.5-14B-Base,51.17566,51.17566,62.6556,62.6556,65.42185,65.42185,50.89903,50.89903
 Qwen1.5-14B-Chat,62.93223,64.03873,64.59198,64.31535,63.34716,63.7621,65.42185,65.9751
+Deepseek-R1-Distill-Qwen-14B,60.99749433241857,60.99749433241857,,,58.225748717336835,58.225748717336835,,
+Deepseek-R1-Distill-Qwen-32B,69.02696575587639,69.02696575587639,,,67.8988187567116,67.8988187567116,,
+Claude-3-Opus,67.64288271089369,67.64288271089369,,,,,,

data_v2/zabbix_zh_mc_gen.csv

@@ -14,14 +14,14 @@ Mistral-7B,6.0,6.0,42.0,42.0,11.0,11.0,44.0,44.0
 Qwen-14B-Chat,36.0,36.0,39.0,41.0,44.0,40.0,47.0,43.0
 Qwen-72B-Chat,46.0,46.0,44.0,44.0,45.0,45.0,61.0,61.0
 Yi-34B-Chat,40.0,40.0,40.0,40.0,42.0,42.0,42.0,42.0
-Claude-3-Opus,61.71875,61.71875,,,,,,
 Deepseek-R1-Distill-Llama-8B,34.89583333333333,34.89583333333333,36.02430555555556,36.02430555555556,25.260416666666664,25.260416666666664,36.63194444444444,36.63194444444444
 Deepseek-R1-Distill-Qwen-1.5B,23.4375,23.4375,25.78125,25.78125,16.40625,16.40625,32.11805555555556,32.11805555555556
-Deepseek-R1-Distill-Qwen-14B,51.822916666666664,51.822916666666664,,,49.479166666666664,49.479166666666664,,
-Deepseek-R1-Distill-Qwen-32B,58.94097222222222,58.94097222222222,,,58.94097222222222,58.94097222222222,,
 Deepseek-R1-Distill-Qwen-7B,25.43402777777778,25.43402777777778,28.993055555555557,28.993055555555557,23.697916666666664,23.697916666666664,32.89930555555556,32.89930555555556
 Gemma-2B,25.0,25.0,32.0,32.0,24.0,24.0,30.0,30.0
 Gemma-7B,22.0,22.0,44.0,44.0,28.0,28.0,40.0,40.0
 Meta-Llama-3-8B-Instruct,39.670138888888886,39.670138888888886,37.58680555555556,37.58680555555556,30.381944444444443,30.381944444444443,33.072916666666664,33.072916666666664
 Qwen1.5-14B-Base,38.0,38.0,39.0,39.0,48.0,48.0,36.0,36.0
 Qwen1.5-14B-Chat,34.0,34.0,45.0,43.0,42.0,39.0,48.0,49.0
+Deepseek-R1-Distill-Qwen-14B,51.822916666666664,51.822916666666664,,,49.479166666666664,49.479166666666664,,
+Deepseek-R1-Distill-Qwen-32B,58.94097222222222,58.94097222222222,,,58.94097222222222,58.94097222222222,,
+Claude-3-Opus,61.71875,61.71875,,,,,,

data_v2/zjyd_en_mc_gen.csv

@@ -1,8 +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-3.5-turbo,87.03703703703704,84.11680851851852,88.39286,89.28571,86.11111111111111,83.65384615555556,86.60714286,88.39285714
-GPT-4,87.03703703703704,87.03703703703704,,,87.03703703703704,87.03703703703704,,
 Gemma-2B,,26.49573,62.5,62.5,,58.97435897,75.0,75.0
-Gemma-7B,,77.77778,75.89286,75.89286,,76.06837607,,
 JIUTIAN-75B-net,83.33333333333334,83.33333333333334,87.03703703703704,87.03703703703704,82.4074074074074,82.4074074074074,87.03703703703704,87.03703703703704
 Qwen1.5-0.5B-Base,,65.17857,75.0,75.0,,56.25,57.14285714,57.14285714
 Qwen1.5-0.5B-Chat,,0.0,54.46429,53.57143,,19.64285714,16.96428571,17.85714286
@@ -10,10 +8,10 @@ Qwen1.5-1.8B-Base,,71.42857,71.42857,71.42857,,70.53571429,80.35714286,80.357142
 Qwen1.5-1.8B-Chat,,69.64286,67.85714,77.67857,,66.07142857,68.75,75.0
 Qwen1.5-14B-Base,,76.92308,,,,78.63247863,83.03571429,83.03571429
 Qwen1.5-14B-Chat,,23.21429,,,,78.57142857,80.35714286,83.92857143
-JIUTIAN-75B-net,82.4074074074074,82.4074074074074,87.96296296296296,87.96296296296296,84.25925925925925,84.25925925925925,87.96296296296296,87.96296296296296
-Chmobile2026,22.22222222222222,22.22222222222222,87.03703703703704,87.03703703703704,3.7037037037037033,3.7037037037037033,87.03703703703704,87.03703703703704
 Deepseek-R1-Distill-Llama-8B,37.03703703703704,37.03703703703704,41.2037037037037,41.2037037037037,22.685185185185187,22.685185185185187,31.01851851851852,31.01851851851852
 Deepseek-R1-Distill-Qwen-1.5B,37.03703703703704,37.03703703703704,27.77777777777778,27.77777777777778,15.74074074074074,15.74074074074074,30.09259259259259,30.09259259259259
+Deepseek-R1-Distill-Qwen-7B,22.685185185185187,22.685185185185187,37.5,37.5,21.296296296296298,21.296296296296298,31.944444444444443,31.944444444444443
+GPT-4,87.03703703703704,87.03703703703704,,,87.03703703703704,87.03703703703704,,
+Gemma-7B,,77.77778,75.89286,75.89286,,76.06837607,,
 Deepseek-R1-Distill-Qwen-14B,69.44444444444444,69.44444444444444,,,19.90740740740741,19.90740740740741,,
 Deepseek-R1-Distill-Qwen-32B,66.2037037037037,66.2037037037037,,,21.75925925925926,21.75925925925926,,
-Deepseek-R1-Distill-Qwen-7B,22.685185185185187,22.685185185185187,37.5,37.5,21.296296296296298,21.296296296296298,31.944444444444443,31.944444444444443

data_v2/zjyd_zh_mc_gen.csv

@@ -13,7 +13,7 @@ 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
-JIUTIAN-75B-net,65.74074074074075,65.74074074074075,89.81481481481481,89.81481481481481,9.25925925925926,9.25925925925926,93.51851851851852,93.51851851851852
+JIUTIAN-75B-net,84.25925925925925,84.25925925925925,89.81481481481481,89.81481481481481,85.18518518518519,85.18518518518519,93.51851851851852,93.51851851851852
 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
@@ -22,16 +22,14 @@ 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
-JIUTIAN-75B-net,80.55555555555556,80.55555555555556,88.88888888888889,88.88888888888889,85.18518518518519,85.18518518518519,88.88888888888889,88.88888888888889
-Chmobile2026,65.74074074074075,65.74074074074075,89.81481481481481,89.81481481481481,9.25925925925926,9.25925925925926,93.51851851851852,93.51851851851852
-Claude-3-Opus,68.05555555555556,68.05555555555556,,,,,,
 Deepseek-R1-Distill-Llama-8B,32.407407407407405,32.407407407407405,43.05555555555556,43.05555555555556,37.96296296296296,37.96296296296296,48.61111111111111,48.61111111111111
 Deepseek-R1-Distill-Qwen-1.5B,30.555555555555557,30.555555555555557,47.22222222222222,47.22222222222222,38.425925925925924,38.425925925925924,35.648148148148145,35.648148148148145
-Deepseek-R1-Distill-Qwen-14B,64.81481481481481,64.81481481481481,,,50.0,50.0,,
-Deepseek-R1-Distill-Qwen-32B,81.94444444444444,81.94444444444444,,,67.5925925925926,67.5925925925926,,
 Deepseek-R1-Distill-Qwen-7B,49.53703703703704,49.53703703703704,35.648148148148145,35.648148148148145,33.7962962962963,33.7962962962963,61.11111111111111,61.11111111111111
 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
 Meta-Llama-3-8B-Instruct,63.425925925925924,63.425925925925924,0.0,0.0,66.2037037037037,66.2037037037037,25.0,25.0
 Qwen1.5-14B-Base,49.1,49.1,49.9,49.9,62.5,62.5,41.3,41.3
 Qwen1.5-14B-Chat,38.6,38.9,48.8,50.5,54.6,55.2,52.1,52.7
+Deepseek-R1-Distill-Qwen-14B,64.81481481481481,64.81481481481481,,,50.0,50.0,,
+Deepseek-R1-Distill-Qwen-32B,81.94444444444444,81.94444444444444,,,67.5925925925926,67.5925925925926,,
+Claude-3-Opus,68.05555555555556,68.05555555555556,,,,,,

data_v2/zte_en_mc_gen.csv

@@ -20,13 +20,8 @@ Qwen-14B-Chat,33.71,36.25,41.24,42.51,51.19,50.39,57.18,59.18
 Qwen-72B-Chat,53.19,53.19,55.25,55.52,58.13,58.13,58.72,58.99
 Qwen-7B-Chat,33.37,33.74,32.97,34.1,32.98,32.7,36.6,36.65
 Yi-34B-Chat,38.24,37.04,48.24,52.1,61.33,61.19,53.53,53.39
-JIUTIAN-75B-net,56.99999999999999,56.99999999999999,61.4,61.4,56.99999999999999,56.99999999999999,55.400000000000006,55.400000000000006
-Chmobile2026,9.8,9.8,68.4,68.4,7.000000000000001,7.000000000000001,67.80000000000001,67.80000000000001
-Claude-3-Opus,49.599999999999994,49.599999999999994,,,,,,
 Deepseek-R1-Distill-Llama-8B,17.6,17.6,31.799999999999997,31.799999999999997,24.099999999999998,24.099999999999998,33.8,33.8
 Deepseek-R1-Distill-Qwen-1.5B,19.0,19.0,20.9,20.9,22.700000000000003,22.700000000000003,29.6,29.6
-Deepseek-R1-Distill-Qwen-14B,35.7,35.7,,,29.6,29.6,,
-Deepseek-R1-Distill-Qwen-32B,57.8,57.8,,,30.9,30.9,,
 Deepseek-R1-Distill-Qwen-7B,21.0,21.0,27.0,27.0,26.700000000000003,26.700000000000003,32.4,32.4
 Gemma-2B,20.1,20.1,24.2,24.2,31.2,31.2,35.5,35.5
 Gemma-7B,23.1,23.1,34.4,34.4,21.4,21.4,33.1,33.1
@@ -34,3 +29,6 @@ Meta-Llama-3-70B-Instruct,38.9,38.9,63.4,63.4,37.6,37.6,59.0,59.0
 Meta-Llama-3-8B-Instruct,24.7,24.7,35.4,35.4,19.7,19.7,32.9,32.9
 Qwen1.5-14B-Base,34.0,34.0,42.8,42.8,57.9,57.9,40.2,40.2
 Qwen1.5-14B-Chat,34.5,35.6,41.7,41.1,33.2,34.7,46.2,47.4
+Deepseek-R1-Distill-Qwen-14B,35.7,35.7,,,29.6,29.6,,
+Deepseek-R1-Distill-Qwen-32B,57.8,57.8,,,30.9,30.9,,
+Claude-3-Opus,49.599999999999994,49.599999999999994,,,,,,

data_v2/zte_zh_mc_gen.csv

@@ -13,7 +13,7 @@ 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
-JIUTIAN-75B-net,47.8,47.8,72.8,72.8,18.0,18.0,80.0,80.0
+JIUTIAN-75B-net,78.60000000000001,78.60000000000001,72.8,72.8,76.4,76.4,80.0,80.0
 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
@@ -22,13 +22,8 @@ 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
-JIUTIAN-75B-net,64.2,64.2,66.60000000000001,66.60000000000001,64.0,64.0,67.80000000000001,67.80000000000001
-Chmobile2026,47.8,47.8,72.8,72.8,18.0,18.0,80.0,80.0
-Claude-3-Opus,51.4,51.4,,,,,,
 Deepseek-R1-Distill-Llama-8B,25.0,25.0,32.1,32.1,30.5,30.5,34.6,34.6
 Deepseek-R1-Distill-Qwen-1.5B,28.299999999999997,28.299999999999997,24.6,24.6,23.1,23.1,31.300000000000004,31.300000000000004
-Deepseek-R1-Distill-Qwen-14B,46.5,46.5,,,52.3,52.3,,
-Deepseek-R1-Distill-Qwen-32B,65.5,65.5,,,67.39999999999999,67.39999999999999,,
 Deepseek-R1-Distill-Qwen-7B,30.900000000000002,30.900000000000002,29.400000000000002,29.400000000000002,32.6,32.6,35.599999999999994,35.599999999999994
 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
@@ -36,3 +31,6 @@ Meta-Llama-3-70B-Instruct,31.1,31.1,37.4,37.4,51.10000000000001,51.1000000000000
 Meta-Llama-3-8B-Instruct,31.1,31.1,34.3,34.3,36.0,36.0,37.1,37.1
 Qwen1.5-14B-Base,49.1,49.1,49.9,49.9,62.5,62.5,41.3,41.3
 Qwen1.5-14B-Chat,38.6,38.9,48.8,50.5,54.6,55.2,52.1,52.7
+Deepseek-R1-Distill-Qwen-14B,46.5,46.5,,,52.3,52.3,,
+Deepseek-R1-Distill-Qwen-32B,65.5,65.5,,,67.39999999999999,67.39999999999999,,
+Claude-3-Opus,51.4,51.4,,,,,,