diff --git a/results/cross_lingual/few_shot/cross_logiqa.csv b/results/cross_lingual/few_shot/cross_logiqa.csv
index c70b781c2b64d574dce967ddf17d8399f2a2a234..0583fe8723e2bc420b72c71ce0be88a88765df9b 100644
--- a/results/cross_lingual/few_shot/cross_logiqa.csv
+++ b/results/cross_lingual/few_shot/cross_logiqa.csv
@@ -1 +1,5 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Meta-Llama-3.1-70B,0.6241883116883117,0.5274350649350649,0.5717473426837402,0.7386363636363636,0.6306818181818182,0.6193181818181818,0.6079545454545454,0.6022727272727273,0.625,0.5454545454545454
+Meta-Llama-3-8B,0.4569805194805195,0.25519480519480514,0.32750096946546897,0.5340909090909091,0.5284090909090909,0.44886363636363635,0.4602272727272727,0.38636363636363635,0.44886363636363635,0.39204545454545453
+llama3-8b-cpt-sea-lionv2-base,0.4553571428571429,0.2600649350649351,0.33105611198328916,0.45454545454545453,0.48295454545454547,0.48863636363636365,0.48295454545454547,0.4431818181818182,0.45454545454545453,0.3806818181818182
+Meta-Llama-3.1-8B,0.4586038961038961,0.28230519480519484,0.3494794808137755,0.5056818181818182,0.5170454545454546,0.4602272727272727,0.4943181818181818,0.39204545454545453,0.45454545454545453,0.38636363636363635
diff --git a/results/cross_lingual/few_shot/cross_mmlu.csv b/results/cross_lingual/few_shot/cross_mmlu.csv
index c70b781c2b64d574dce967ddf17d8399f2a2a234..1522e86d89224e2320884ab5035a42884a90b772 100644
--- a/results/cross_lingual/few_shot/cross_mmlu.csv
+++ b/results/cross_lingual/few_shot/cross_mmlu.csv
@@ -1 +1,5 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Meta-Llama-3.1-70B,0.74,0.6445714285714286,0.688997110969635,0.7933333333333333,0.72,0.7466666666666667,0.7333333333333333,0.7466666666666667,0.7466666666666667,0.6933333333333334
+Meta-Llama-3-8B,0.5295238095238095,0.29771428571428576,0.381140094029779,0.6133333333333333,0.4666666666666667,0.58,0.5,0.5333333333333333,0.47333333333333333,0.54
+llama3-8b-cpt-sea-lionv2-base,0.5114285714285715,0.33390476190476204,0.404026266610288,0.6333333333333333,0.47333333333333333,0.52,0.47333333333333333,0.52,0.49333333333333335,0.4666666666666667
+Meta-Llama-3.1-8B,0.5304761904761904,0.34419047619047627,0.4174958519516044,0.68,0.5,0.5533333333333333,0.4866666666666667,0.5333333333333333,0.5133333333333333,0.44666666666666666
diff --git a/results/cross_lingual/few_shot/cross_xquad.csv b/results/cross_lingual/few_shot/cross_xquad.csv
index c70b781c2b64d574dce967ddf17d8399f2a2a234..e188a55123ec6263e655d85cc81159ae8580808e 100644
--- a/results/cross_lingual/few_shot/cross_xquad.csv
+++ b/results/cross_lingual/few_shot/cross_xquad.csv
@@ -1 +1,5 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Meta-Llama-3.1-70B,0.9588235294117647,0.9382352941176471,0.9484176926084648,0.9647058823529412,0.9571428571428572,0.9554621848739496,0.957983193277311,,,
+Meta-Llama-3-8B,0.8951680672268908,0.8123949579831933,0.851775323760744,0.9277310924369748,0.8756302521008403,0.8907563025210085,0.8865546218487395,,,
+llama3-8b-cpt-sea-lionv2-base,0.9054621848739495,0.8464285714285714,0.8749507477272823,0.9193277310924369,0.8899159663865546,0.9126050420168067,0.9,,,
+Meta-Llama-3.1-8B,0.9063025210084034,0.8340336134453781,0.8686675538861947,0.9319327731092437,0.8890756302521008,0.9117647058823529,0.892436974789916,,,
diff --git a/results/cross_lingual/zero_shot/cross_logiqa.csv b/results/cross_lingual/zero_shot/cross_logiqa.csv
index c70b781c2b64d574dce967ddf17d8399f2a2a234..f2d4ca92181686906e05e50076086ba92efe94f9 100644
--- a/results/cross_lingual/zero_shot/cross_logiqa.csv
+++ b/results/cross_lingual/zero_shot/cross_logiqa.csv
@@ -1 +1,24 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Qwen2-7B-Instruct,0.564935064935065,0.48279220779220783,0.5206435955861558,0.6590909090909091,0.7045454545454546,0.5340909090909091,0.5738636363636364,0.5397727272727273,0.5113636363636364,0.4318181818181818
+Meta-Llama-3.1-8B-Instruct,0.4472402597402597,0.43717532467532455,0.44215052105151864,0.5227272727272727,0.4602272727272727,0.4715909090909091,0.4715909090909091,0.4147727272727273,0.3977272727272727,0.39204545454545453
+Qwen2_5_32B_Instruct,0.6931818181818182,0.6397727272727273,0.6654072695772988,0.7727272727272727,0.7897727272727273,0.6704545454545454,0.6761363636363636,0.6875,0.6875,0.5681818181818182
+Qwen2_5_7B_Instruct,0.599025974025974,0.5034090909090908,0.5470709896292291,0.7102272727272727,0.7215909090909091,0.6136363636363636,0.6022727272727273,0.5738636363636364,0.5511363636363636,0.42045454545454547
+Qwen2_5_1_5B_Instruct,0.46834415584415584,0.348538961038961,0.3996561615557665,0.5511363636363636,0.5909090909090909,0.4659090909090909,0.5113636363636364,0.4375,0.375,0.3465909090909091
+Qwen2-72B-Instruct,0.6728896103896104,0.6762987012987012,0.6745898487968579,0.75,0.8068181818181818,0.6534090909090909,0.6193181818181818,0.625,0.6534090909090909,0.6022727272727273
+cross_openhermes_llama3_8b_4096_inst,0.4496753246753246,0.49188311688311687,0.4698331840074224,0.5170454545454546,0.4318181818181818,0.4318181818181818,0.4659090909090909,0.4602272727272727,0.4602272727272727,0.3806818181818182
+Meta-Llama-3-8B-Instruct,0.4610389610389611,0.45097402597402597,0.4559509553669637,0.5965909090909091,0.48295454545454547,0.5,0.4602272727272727,0.42045454545454547,0.4034090909090909,0.36363636363636365
+Meta-Llama-3.1-70B-Instruct,0.6566558441558442,0.598051948051948,0.6259852839118454,0.7443181818181818,0.7215909090909091,0.6647727272727273,0.6534090909090909,0.6193181818181818,0.625,0.5681818181818182
+Qwen2_5_3B_Instruct,0.4878246753246754,0.3594155844155844,0.41388918606681485,0.6079545454545454,0.6420454545454546,0.45454545454545453,0.4602272727272727,0.48295454545454547,0.42045454545454547,0.3465909090909091
+SeaLLMs-v3-7B-Chat,0.5551948051948051,0.5142857142857142,0.5339578453833284,0.6022727272727273,0.6647727272727273,0.5738636363636364,0.5454545454545454,0.5170454545454546,0.5,0.48295454545454547
+Qwen2_5_72B_Instruct,0.7248376623376623,0.6852272727272727,0.7044761161663122,0.8011363636363636,0.7954545454545454,0.7272727272727273,0.6704545454545454,0.7159090909090909,0.7159090909090909,0.6477272727272727
+gemma-2-9b-it,0.6185064935064934,0.5592532467532466,0.5873893507784849,0.6647727272727273,0.6761363636363636,0.5625,0.6193181818181818,0.5795454545454546,0.6420454545454546,0.5852272727272727
+Meta-Llama-3-70B-Instruct,0.6306818181818182,0.6186688311688312,0.6246175698800746,0.7102272727272727,0.6875,0.6420454545454546,0.6193181818181818,0.6022727272727273,0.6136363636363636,0.5397727272727273
+Qwen2_5_14B_Instruct,0.6436688311688312,0.5938311688311688,0.6177464473895627,0.75,0.7386363636363636,0.6306818181818182,0.6420454545454546,0.6136363636363636,0.5965909090909091,0.5340909090909091
+sg_llama3_8192_8b,0.49594155844155846,0.468831168831169,0.4820054587349027,0.5795454545454546,0.48295454545454547,0.5397727272727273,0.48863636363636365,0.5,0.48295454545454547,0.3977272727272727
+sg_llama3_70b_inst,0.6217532467532468,0.5629870129870129,0.590912649920049,0.7272727272727273,0.6590909090909091,0.6477272727272727,0.6079545454545454,0.6136363636363636,0.5795454545454546,0.5170454545454546
+gemma-2-2b-it,0.4780844155844156,0.4448051948051948,0.46084478401384643,0.5568181818181818,0.5,0.5,0.48863636363636365,0.4375,0.4602272727272727,0.4034090909090909
+llama3-8b-cpt-sea-lionv2-instruct,0.48538961038961037,0.4472402597402597,0.46553468284769084,0.5284090909090909,0.5113636363636364,0.5227272727272727,0.5227272727272727,0.48863636363636365,0.44886363636363635,0.375
+Qwen2_5_0_5B_Instruct,0.3538961038961039,0.1978896103896103,0.25383898238962527,0.45454545454545453,0.39204545454545453,0.3465909090909091,0.375,0.3409090909090909,0.30113636363636365,0.26704545454545453
+GPT4o_0513,0.7159090909090909,0.6941558441558444,0.7048646724637749,0.7613636363636364,0.7670454545454546,0.6988636363636364,0.6988636363636364,0.7045454545454546,0.6761363636363636,0.7045454545454546
+cross_openhermes_llama3_70b_4096_inst,0.6071428571428571,0.5717532467532467,0.5889168666140888,0.6988636363636364,0.6363636363636364,0.625,0.5681818181818182,0.5965909090909091,0.5965909090909091,0.5284090909090909
+cross_openhermes_llama3_8b_4096_2_inst,0.48214285714285715,0.4417207792207793,0.4610475185885475,0.5454545454545454,0.4943181818181818,0.4943181818181818,0.4602272727272727,0.48295454545454547,0.5227272727272727,0.375
diff --git a/results/cross_lingual/zero_shot/cross_mmlu.csv b/results/cross_lingual/zero_shot/cross_mmlu.csv
index c70b781c2b64d574dce967ddf17d8399f2a2a234..7ce195f6e2680c112e77a2795b6803bf6534e54d 100644
--- a/results/cross_lingual/zero_shot/cross_mmlu.csv
+++ b/results/cross_lingual/zero_shot/cross_mmlu.csv
@@ -1 +1,24 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Qwen2-7B-Instruct,0.6628571428571428,0.5257142857142858,0.5863736263242921,0.76,0.6666666666666666,0.72,0.5933333333333334,0.7066666666666667,0.6133333333333333,0.58
+Meta-Llama-3.1-8B-Instruct,0.5619047619047618,0.5020952380952383,0.5303189947159841,0.66,0.5266666666666666,0.5733333333333334,0.5266666666666666,0.5533333333333333,0.5533333333333333,0.54
+Qwen2_5_32B_Instruct,0.8019047619047619,0.7386666666666668,0.7689878008073214,0.8533333333333334,0.8533333333333334,0.82,0.7933333333333333,0.8,0.7866666666666666,0.7066666666666667
+Qwen2_5_7B_Instruct,0.6733333333333332,0.580952380952381,0.6237408250578389,0.7666666666666667,0.7066666666666667,0.72,0.6666666666666666,0.6866666666666666,0.6266666666666667,0.54
+Qwen2_5_1_5B_Instruct,0.5076190476190475,0.3721904761904762,0.42948154099799957,0.6,0.6066666666666667,0.5333333333333333,0.4866666666666667,0.5666666666666667,0.4,0.36
+Qwen2-72B-Instruct,0.779047619047619,0.7611428571428573,0.7699911663398871,0.8133333333333334,0.7933333333333333,0.7933333333333333,0.7333333333333333,0.7666666666666667,0.78,0.7733333333333333
+cross_openhermes_llama3_8b_4096_inst,0.5523809523809523,0.5384761904761904,0.5453399518902743,0.6533333333333333,0.56,0.5333333333333333,0.5066666666666667,0.5466666666666666,0.5733333333333334,0.49333333333333335
+Meta-Llama-3-8B-Instruct,0.5733333333333334,0.4742857142857144,0.5191272726777197,0.7133333333333334,0.5866666666666667,0.5733333333333334,0.5866666666666667,0.5066666666666667,0.5333333333333333,0.5133333333333333
+Meta-Llama-3.1-70B-Instruct,0.7638095238095238,0.7716190476190474,0.7676944251955988,0.8,0.74,0.7666666666666667,0.7666666666666667,0.76,0.7666666666666667,0.7466666666666667
+Qwen2_5_3B_Instruct,0.5857142857142856,0.48952380952380964,0.533316462053399,0.6933333333333334,0.6666666666666666,0.64,0.5266666666666666,0.6333333333333333,0.5466666666666666,0.3933333333333333
+SeaLLMs-v3-7B-Chat,0.6628571428571429,0.6135238095238095,0.6372370860992635,0.74,0.6933333333333334,0.6933333333333334,0.6466666666666666,0.68,0.6,0.5866666666666667
+Qwen2_5_72B_Instruct,0.8123809523809525,0.8140952380952383,0.8132371917701643,0.8533333333333334,0.8333333333333334,0.84,0.7933333333333333,0.8066666666666666,0.7733333333333333,0.7866666666666666
+gemma-2-9b-it,0.7161904761904762,0.7163809523809525,0.7162857015727578,0.7733333333333333,0.74,0.7066666666666667,0.64,0.7266666666666667,0.6933333333333334,0.7333333333333333
+Meta-Llama-3-70B-Instruct,0.758095238095238,0.7316190476190477,0.7446218665971989,0.7933333333333333,0.7466666666666667,0.7733333333333333,0.7466666666666667,0.7733333333333333,0.7333333333333333,0.74
+Qwen2_5_14B_Instruct,0.7266666666666666,0.680952380952381,0.7030672078887086,0.78,0.7533333333333333,0.7533333333333333,0.7266666666666667,0.7466666666666667,0.68,0.6466666666666666
+sg_llama3_8192_8b,0.5876190476190476,0.5207619047619048,0.5521740766611207,0.7,0.58,0.6333333333333333,0.5466666666666666,0.5533333333333333,0.5666666666666667,0.5333333333333333
+sg_llama3_70b_inst,0.7342857142857142,0.7079999999999999,0.7209033280007295,0.82,0.6866666666666666,0.7333333333333333,0.6933333333333334,0.78,0.7266666666666667,0.7
+gemma-2-2b-it,0.5780952380952381,0.5480000000000002,0.5626454667971265,0.7,0.5866666666666667,0.5866666666666667,0.5333333333333333,0.5666666666666667,0.5333333333333333,0.54
+llama3-8b-cpt-sea-lionv2-instruct,0.6104761904761905,0.5685714285714286,0.5887791368067445,0.72,0.6,0.6133333333333333,0.58,0.6333333333333333,0.5933333333333334,0.5333333333333333
+Qwen2_5_0_5B_Instruct,0.4228571428571429,0.2436190476190476,0.3091364879297727,0.6133333333333333,0.5,0.4266666666666667,0.4066666666666667,0.3933333333333333,0.3333333333333333,0.2866666666666667
+GPT4o_0513,0.8038095238095239,0.8506666666666668,0.8265745643832277,0.8266666666666667,0.7933333333333333,0.8,0.7666666666666667,0.7933333333333333,0.8266666666666667,0.82
+cross_openhermes_llama3_70b_4096_inst,0.7257142857142858,0.7375238095238097,0.7315713913287366,0.8,0.7066666666666667,0.7466666666666667,0.6733333333333333,0.7666666666666667,0.7333333333333333,0.6533333333333333
+cross_openhermes_llama3_8b_4096_2_inst,0.5666666666666667,0.5346666666666665,0.5502017755755465,0.6533333333333333,0.56,0.5266666666666666,0.5533333333333333,0.6,0.5533333333333333,0.52
diff --git a/results/cross_lingual/zero_shot/cross_xquad.csv b/results/cross_lingual/zero_shot/cross_xquad.csv
index c70b781c2b64d574dce967ddf17d8399f2a2a234..a05059879241fdeea1334d3801fd28d7b7b5e173 100644
--- a/results/cross_lingual/zero_shot/cross_xquad.csv
+++ b/results/cross_lingual/zero_shot/cross_xquad.csv
@@ -1 +1,23 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
+Qwen2-7B-Instruct,0.9418067226890756,0.9046218487394958,0.9228398561109394,0.957983193277311,0.9336134453781513,0.9436974789915966,0.9319327731092437,,,
+Meta-Llama-3.1-8B-Instruct,0.9287815126050419,0.8867647058823529,0.9072869161050563,0.9420168067226891,0.9193277310924369,0.9361344537815126,0.9176470588235294,,,
+Qwen2_5_7B_Instruct,0.9460084033613445,0.9178571428571428,0.9317201790045005,0.9554621848739496,0.9487394957983193,0.9445378151260504,0.9352941176470588,,,
+Qwen2_5_1_5B_Instruct,0.8939075630252101,0.8308823529411764,0.8612434620121144,0.9100840336134454,0.9,0.8957983193277311,0.8697478991596639,,,
+Qwen2-72B-Instruct,0.9613445378151261,0.9516806722689075,0.956488195931227,0.9638655462184874,0.9596638655462185,0.9596638655462185,0.9621848739495799,,,
+cross_openhermes_llama3_8b_4096_inst,0.9052521008403361,0.8705882352941177,0.8875818539385091,0.9168067226890756,0.9025210084033614,0.9050420168067227,0.8966386554621849,,,
+Meta-Llama-3-8B-Instruct,0.9210084033613445,0.880672268907563,0.9003888121913395,0.9411764705882353,0.9033613445378151,0.9260504201680673,0.9134453781512605,,,
+Meta-Llama-3.1-70B-Instruct,0.9615546218487395,0.9512605042016806,0.9563798632627071,0.9647058823529412,0.9512605042016806,0.9647058823529412,0.965546218487395,,,
+Qwen2_5_3B_Instruct,0.9378151260504202,0.8924369747899159,0.9145635113049859,0.9504201680672268,0.9327731092436975,0.9378151260504202,0.9302521008403362,,,
+SeaLLMs-v3-7B-Chat,0.9403361344537815,0.917016806722689,0.9285300818164836,0.9537815126050421,0.9378151260504202,0.9394957983193277,0.9302521008403362,,,
+Qwen2_5_72B_Instruct,0.9682773109243697,0.9632352941176471,0.9657497216354985,0.9714285714285714,0.9638655462184874,0.9680672268907563,0.9697478991596639,,,
+gemma-2-9b-it,0.9567226890756303,0.9350840336134454,0.9457796088507574,0.9663865546218487,0.9411764705882353,0.9588235294117647,0.9605042016806723,,,
+Meta-Llama-3-70B-Instruct,0.9592436974789916,0.9422268907563025,0.9506591499208973,0.9714285714285714,0.9403361344537815,0.9596638655462185,0.965546218487395,,,
+Qwen2_5_14B_Instruct,0.9581932773109244,0.9474789915966386,0.9528060148705768,0.965546218487395,0.9529411764705882,0.9571428571428572,0.9571428571428572,,,
+sg_llama3_8192_8b,0.899579831932773,0.8611344537815127,0.8799374134072335,0.9201680672268907,0.8831932773109243,0.9117647058823529,0.8831932773109243,,,
+sg_llama3_70b_inst,0.9552521008403361,0.9453781512605042,0.9502894779607259,0.9663865546218487,0.9436974789915966,0.957983193277311,0.9529411764705882,,,
+gemma-2-2b-it,0.917016806722689,0.8665966386554622,0.8910940700869288,0.934453781512605,0.9025210084033614,0.9193277310924369,0.9117647058823529,,,
+llama3-8b-cpt-sea-lionv2-instruct,0.9365546218487395,0.9086134453781513,0.9223724784871395,0.9420168067226891,0.926890756302521,0.9436974789915966,0.9336134453781513,,,
+Qwen2_5_0_5B_Instruct,0.6584033613445378,0.48172268907563026,0.5563732844778362,0.692436974789916,0.673109243697479,0.653781512605042,0.6142857142857143,,,
+GPT4o_0513,0.9605042016806723,0.951890756302521,0.9561780814209724,0.965546218487395,0.9537815126050421,0.9630252100840336,0.9596638655462185,,,
+cross_openhermes_llama3_70b_4096_inst,0.9510504201680672,0.9464285714285714,0.9487338668359928,0.9621848739495799,0.9512605042016806,0.9487394957983193,0.9420168067226891,,,
+cross_openhermes_llama3_8b_4096_2_inst,0.9180672268907563,0.871218487394958,0.8940295385002202,0.9310924369747899,0.9218487394957983,0.9084033613445378,0.9109243697478991,,,
diff --git a/results/cultural_reasoning/few_shot/cn_eval.csv b/results/cultural_reasoning/few_shot/cn_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..f3dcf0c7f2d4babc2267e052420979fd9e233e3e 100644
--- a/results/cultural_reasoning/few_shot/cn_eval.csv
+++ b/results/cultural_reasoning/few_shot/cn_eval.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.5904761904761905
+Meta-Llama-3-8B,0.42857142857142855
+llama3-8b-cpt-sea-lionv2-base,0.38095238095238093
+Meta-Llama-3.1-8B,0.4380952380952381
diff --git a/results/cultural_reasoning/few_shot/ph_eval.csv b/results/cultural_reasoning/few_shot/ph_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..ccaf1883b6a596625a21dfe98283d873626911a7 100644
--- a/results/cultural_reasoning/few_shot/ph_eval.csv
+++ b/results/cultural_reasoning/few_shot/ph_eval.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.66
+Meta-Llama-3-8B,0.5
+llama3-8b-cpt-sea-lionv2-base,0.54
+Meta-Llama-3.1-8B,0.52
diff --git a/results/cultural_reasoning/few_shot/sg_eval.csv b/results/cultural_reasoning/few_shot/sg_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..b0974f54dfc062e9cb88e83b300fcaf7722ede5b 100644
--- a/results/cultural_reasoning/few_shot/sg_eval.csv
+++ b/results/cultural_reasoning/few_shot/sg_eval.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7475728155339806
+Meta-Llama-3-8B,0.6601941747572816
+llama3-8b-cpt-sea-lionv2-base,0.6310679611650486
+Meta-Llama-3.1-8B,0.6504854368932039
diff --git a/results/cultural_reasoning/few_shot/sg_eval_v1_cleaned.csv b/results/cultural_reasoning/few_shot/sg_eval_v1_cleaned.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..469db5d46a426b2e000f3abb02b68fcffd7f0d68 100644
--- a/results/cultural_reasoning/few_shot/sg_eval_v1_cleaned.csv
+++ b/results/cultural_reasoning/few_shot/sg_eval_v1_cleaned.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7794117647058824
+Meta-Llama-3-8B,0.6470588235294118
+llama3-8b-cpt-sea-lionv2-base,0.6470588235294118
+Meta-Llama-3.1-8B,0.6029411764705882
diff --git a/results/cultural_reasoning/few_shot/us_eval.csv b/results/cultural_reasoning/few_shot/us_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..30cdc7aec6ec17aec63de2e473b6f90bb5e48ccb 100644
--- a/results/cultural_reasoning/few_shot/us_eval.csv
+++ b/results/cultural_reasoning/few_shot/us_eval.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.8691588785046729
+Meta-Llama-3-8B,0.6542056074766355
+llama3-8b-cpt-sea-lionv2-base,0.6542056074766355
+Meta-Llama-3.1-8B,0.7009345794392523
diff --git a/results/cultural_reasoning/zero_shot/cn_eval.csv b/results/cultural_reasoning/zero_shot/cn_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..5b85cb2989788e1c9912e34e5a0e68db9a500a15 100644
--- a/results/cultural_reasoning/zero_shot/cn_eval.csv
+++ b/results/cultural_reasoning/zero_shot/cn_eval.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.8285714285714286
+Meta-Llama-3.1-8B-Instruct,0.4857142857142857
+Qwen2_5_32B_Instruct,0.8476190476190476
+Qwen2_5_7B_Instruct,0.8
+Qwen2_5_1_5B_Instruct,0.5523809523809524
+Qwen2-72B-Instruct,0.8285714285714286
+cross_openhermes_llama3_8b_4096_inst,0.47619047619047616
+Meta-Llama-3-8B-Instruct,0.4666666666666667
+Meta-Llama-3.1-70B-Instruct,0.5428571428571428
+Qwen2_5_3B_Instruct,0.7142857142857143
+SeaLLMs-v3-7B-Chat,0.819047619047619
+Qwen2_5_72B_Instruct,0.8761904761904762
+gemma-2-9b-it,0.580952380952381
+Meta-Llama-3-70B-Instruct,0.5333333333333333
+Qwen2_5_14B_Instruct,0.8285714285714286
+sg_llama3_8192_8b,0.47619047619047616
+sg_llama3_70b_inst,0.5523809523809524
+gemma-2-2b-it,0.3619047619047619
+llama3-8b-cpt-sea-lionv2-instruct,0.49523809523809526
+Qwen2_5_0_5B_Instruct,0.3619047619047619
+GPT4o_0513,0.8095238095238095
+cross_openhermes_llama3_70b_4096_inst,0.6095238095238096
+cross_openhermes_llama3_8b_4096_2_inst,0.5142857142857142
diff --git a/results/cultural_reasoning/zero_shot/ph_eval.csv b/results/cultural_reasoning/zero_shot/ph_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..d6180bd64f1d292a01c7cf8d0fd6b62958602568 100644
--- a/results/cultural_reasoning/zero_shot/ph_eval.csv
+++ b/results/cultural_reasoning/zero_shot/ph_eval.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.52
+Meta-Llama-3.1-8B-Instruct,0.6
+Qwen2_5_32B_Instruct,0.7
+Qwen2_5_7B_Instruct,0.55
+Qwen2_5_1_5B_Instruct,0.37
+Qwen2-72B-Instruct,0.62
+cross_openhermes_llama3_8b_4096_inst,0.47
+Meta-Llama-3-8B-Instruct,0.58
+Meta-Llama-3.1-70B-Instruct,0.68
+Qwen2_5_3B_Instruct,0.4
+SeaLLMs-v3-7B-Chat,0.47
+Qwen2_5_72B_Instruct,0.72
+gemma-2-9b-it,0.58
+Meta-Llama-3-70B-Instruct,0.63
+Qwen2_5_14B_Instruct,0.6
+sg_llama3_8192_8b,0.57
+sg_llama3_70b_inst,0.69
+gemma-2-2b-it,0.4
+llama3-8b-cpt-sea-lionv2-instruct,0.56
+Qwen2_5_0_5B_Instruct,0.27
+GPT4o_0513,0.77
+cross_openhermes_llama3_70b_4096_inst,0.68
+cross_openhermes_llama3_8b_4096_2_inst,0.49
diff --git a/results/cultural_reasoning/zero_shot/sg_eval.csv b/results/cultural_reasoning/zero_shot/sg_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..4c784f049059caee1d9510c7849324f267fd0106 100644
--- a/results/cultural_reasoning/zero_shot/sg_eval.csv
+++ b/results/cultural_reasoning/zero_shot/sg_eval.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.6796116504854369
+Meta-Llama-3.1-8B-Instruct,0.5728155339805825
+Qwen2_5_32B_Instruct,0.7184466019417476
+Qwen2_5_7B_Instruct,0.6699029126213593
+Qwen2_5_1_5B_Instruct,0.5048543689320388
+Qwen2-72B-Instruct,0.7378640776699029
+cross_openhermes_llama3_8b_4096_inst,0.6019417475728155
+Meta-Llama-3-8B-Instruct,0.6504854368932039
+Meta-Llama-3.1-70B-Instruct,0.7184466019417476
+Qwen2_5_3B_Instruct,0.6310679611650486
+SeaLLMs-v3-7B-Chat,0.7184466019417476
+Qwen2_5_72B_Instruct,0.7669902912621359
+gemma-2-9b-it,0.6699029126213593
+Meta-Llama-3-70B-Instruct,0.7087378640776699
+Qwen2_5_14B_Instruct,0.7669902912621359
+sg_llama3_8192_8b,0.5533980582524272
+sg_llama3_70b_inst,0.6699029126213593
+gemma-2-2b-it,0.5533980582524272
+llama3-8b-cpt-sea-lionv2-instruct,0.6504854368932039
+Qwen2_5_0_5B_Instruct,0.4077669902912621
+GPT4o_0513,0.8446601941747572
+cross_openhermes_llama3_70b_4096_inst,0.6796116504854369
+cross_openhermes_llama3_8b_4096_2_inst,0.6407766990291263
diff --git a/results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv b/results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..5f7d28a02462a51db62eb8981f08c6736f8db734 100644
--- a/results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv
+++ b/results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.6323529411764706
+Meta-Llama-3.1-8B-Instruct,0.5294117647058824
+Qwen2_5_32B_Instruct,0.6470588235294118
+Qwen2_5_7B_Instruct,0.5882352941176471
+Qwen2_5_1_5B_Instruct,0.47058823529411764
+Qwen2-72B-Instruct,0.6764705882352942
+cross_openhermes_llama3_8b_4096_inst,0.6029411764705882
+Meta-Llama-3-8B-Instruct,0.5882352941176471
+Meta-Llama-3.1-70B-Instruct,0.6617647058823529
+Qwen2_5_3B_Instruct,0.5882352941176471
+SeaLLMs-v3-7B-Chat,0.5882352941176471
+Qwen2_5_72B_Instruct,0.7205882352941176
+gemma-2-9b-it,0.6029411764705882
+Meta-Llama-3-70B-Instruct,0.6617647058823529
+Qwen2_5_14B_Instruct,0.6911764705882353
+sg_llama3_8192_8b,0.47058823529411764
+sg_llama3_70b_inst,0.6176470588235294
+gemma-2-2b-it,0.4852941176470588
+llama3-8b-cpt-sea-lionv2-instruct,0.6617647058823529
+Qwen2_5_0_5B_Instruct,0.36764705882352944
+GPT4o_0513,0.8088235294117647
+cross_openhermes_llama3_70b_4096_inst,0.5882352941176471
+cross_openhermes_llama3_8b_4096_2_inst,0.6029411764705882
diff --git a/results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv b/results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..c3a47348550d07b1c5c7c4829b947674557f455d 100644
--- a/results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv
+++ b/results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv
@@ -1 +1,14 @@
 Model,Accuracy
+Qwen2_5_32B_Instruct,0.8436363636363636
+Qwen2_5_7B_Instruct,0.78
+Qwen2_5_1_5B_Instruct,0.6636363636363637
+cross_openhermes_llama3_8b_4096_inst,0.7490909090909091
+Qwen2_5_3B_Instruct,0.72
+Qwen2_5_72B_Instruct,0.8618181818181818
+Meta-Llama-3-70B-Instruct,0.8381818181818181
+Qwen2_5_14B_Instruct,0.8345454545454546
+sg_llama3_8192_8b,0.76
+sg_llama3_70b_inst,0.8436363636363636
+Qwen2_5_0_5B_Instruct,0.5727272727272728
+cross_openhermes_llama3_70b_4096_inst,0.8381818181818181
+cross_openhermes_llama3_8b_4096_2_inst,0.7654545454545455
diff --git a/results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv b/results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..7b4f8940b7b5774957f0af33a1e89fa356a6a5d9 100644
--- a/results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv
+++ b/results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv
@@ -1 +1,14 @@
 Model,Accuracy
+Qwen2_5_32B_Instruct,53.2
+Qwen2_5_7B_Instruct,50.279999999999994
+Qwen2_5_1_5B_Instruct,44.480000000000004
+cross_openhermes_llama3_8b_4096_inst,51.6
+Qwen2_5_3B_Instruct,47.24
+Qwen2_5_72B_Instruct,53.32
+Meta-Llama-3-70B-Instruct,50.599999999999994
+Qwen2_5_14B_Instruct,53.2
+sg_llama3_8192_8b,53.4
+sg_llama3_70b_inst,51.959999999999994
+Qwen2_5_0_5B_Instruct,35.28
+cross_openhermes_llama3_70b_4096_inst,53.2
+cross_openhermes_llama3_8b_4096_2_inst,52.28
diff --git a/results/cultural_reasoning/zero_shot/us_eval.csv b/results/cultural_reasoning/zero_shot/us_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..e07c8a169e2d562cfc7017aae7dc2a72501789fe 100644
--- a/results/cultural_reasoning/zero_shot/us_eval.csv
+++ b/results/cultural_reasoning/zero_shot/us_eval.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7289719626168224
+Meta-Llama-3.1-8B-Instruct,0.7289719626168224
+Qwen2_5_32B_Instruct,0.8411214953271028
+Qwen2_5_7B_Instruct,0.7663551401869159
+Qwen2_5_1_5B_Instruct,0.5981308411214953
+Qwen2-72B-Instruct,0.8785046728971962
+cross_openhermes_llama3_8b_4096_inst,0.6448598130841121
+Meta-Llama-3-8B-Instruct,0.7009345794392523
+Meta-Llama-3.1-70B-Instruct,0.8411214953271028
+Qwen2_5_3B_Instruct,0.6728971962616822
+SeaLLMs-v3-7B-Chat,0.6915887850467289
+Qwen2_5_72B_Instruct,0.8598130841121495
+gemma-2-9b-it,0.8130841121495327
+Meta-Llama-3-70B-Instruct,0.8691588785046729
+Qwen2_5_14B_Instruct,0.822429906542056
+sg_llama3_8192_8b,0.7009345794392523
+sg_llama3_70b_inst,0.8598130841121495
+gemma-2-2b-it,0.6915887850467289
+llama3-8b-cpt-sea-lionv2-instruct,0.7009345794392523
+Qwen2_5_0_5B_Instruct,0.37383177570093457
+GPT4o_0513,0.8691588785046729
+cross_openhermes_llama3_70b_4096_inst,0.8317757009345794
+cross_openhermes_llama3_8b_4096_2_inst,0.7289719626168224
diff --git a/results/dialogue/few_shot/dream.csv b/results/dialogue/few_shot/dream.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..04add5f0b2e02d84e5ac5b5a73fe96db40411a6a 100644
--- a/results/dialogue/few_shot/dream.csv
+++ b/results/dialogue/few_shot/dream.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.9495345418912298
+Meta-Llama-3-8B,0.8280254777070064
+llama3-8b-cpt-sea-lionv2-base,0.8520333170014699
+Meta-Llama-3.1-8B,0.8569328760411563
diff --git a/results/dialogue/zero_shot/dialogsum.csv b/results/dialogue/zero_shot/dialogsum.csv
index 432ea7efdaa7a932511e6a0f0b394bfd4ea17963..1cdb072c9c18870789d28e2d80627b44bb2f998f 100644
--- a/results/dialogue/zero_shot/dialogsum.csv
+++ b/results/dialogue/zero_shot/dialogsum.csv
@@ -1 +1,24 @@
 Model,Average,ROUGE-1,ROUGE-2,ROUGE-L
+Qwen2-7B-Instruct,0.2092663759873139,0.30486100228371826,0.09413830506038247,0.22879982061784096
+Meta-Llama-3.1-8B-Instruct,0.24990743661648132,0.3515557454075673,0.12563120411564133,0.2725353603262354
+Qwen2_5_32B_Instruct,0.2393912015484827,0.3451081398022419,0.11160543395371676,0.26146003088948944
+Qwen2_5_7B_Instruct,0.2502928721533066,0.35566069744050016,0.12210269253668227,0.27311522648273734
+Qwen2_5_1_5B_Instruct,0.20263242988485167,0.30002072253966694,0.08416670238558713,0.22370986472930096
+Qwen2-72B-Instruct,0.2183280630214023,0.316174552903144,0.10156543495268992,0.23724420120837297
+cross_openhermes_llama3_8b_4096_inst,0.2519360474995096,0.3481981488260775,0.13235699958788102,0.2752529940845703
+Meta-Llama-3-8B-Instruct,0.23978455271183616,0.33971099717559883,0.1203340311564728,0.2593086298034369
+Meta-Llama-3.1-70B-Instruct,0.2526239717396146,0.35714386898604744,0.1258832921736473,0.27484475405914904
+Qwen2_5_3B_Instruct,0.22107390172674926,0.32206286484028823,0.10065030710901035,0.24050853323094928
+SeaLLMs-v3-7B-Chat,0.24891094210680076,0.35393482223136147,0.12172072639345373,0.27107727769558715
+Qwen2_5_72B_Instruct,0.23460549655507293,0.3373580017785426,0.10893746645433498,0.25752102143234123
+gemma-2-9b-it,0.2560682231168516,0.36247455000865003,0.12571639767749476,0.2800137216644101
+Meta-Llama-3-70B-Instruct,0.2557065499979308,0.36058417323628,0.12758087337786866,0.2789546033796438
+Qwen2_5_14B_Instruct,0.2343478938479703,0.3386251381162625,0.10742381514017992,0.2569947282874686
+sg_llama3_8192_8b,0.2708022468830074,0.3774768588431775,0.1387436961438702,0.2961861856619747
+sg_llama3_70b_inst,0.26633840691332344,0.3692028513115729,0.1412505883866801,0.2885617810417173
+gemma-2-2b-it,0.2597323674875989,0.36848124762381895,0.12622684440269072,0.2844890104362872
+llama3-8b-cpt-sea-lionv2-instruct,0.25777587511641403,0.35911990072292727,0.13269121463917308,0.2815165099871418
+Qwen2_5_0_5B_Instruct,0.19408176276624156,0.28989753303423227,0.07842728643649079,0.21392046882800164
+GPT4o_0513,0.2375730297294346,0.3364674648846549,0.11718194476069822,0.25906967954295057
+cross_openhermes_llama3_70b_4096_inst,0.2727448037865066,0.3786585439052446,0.14288118221672744,0.2966946852375478
+cross_openhermes_llama3_8b_4096_2_inst,0.2606665855752626,0.3625849627075515,0.1356024730798863,0.28381232093835007
diff --git a/results/dialogue/zero_shot/dream.csv b/results/dialogue/zero_shot/dream.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..e07fc40a2c1a3fab96411af73d177d8e8206108a 100644
--- a/results/dialogue/zero_shot/dream.csv
+++ b/results/dialogue/zero_shot/dream.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.9353258206761391
+Meta-Llama-3.1-8B-Instruct,0.9039686428221461
+Qwen2_5_32B_Instruct,0.9559039686428221
+Qwen2_5_7B_Instruct,0.9348358647721705
+Qwen2_5_1_5B_Instruct,0.8314551690347869
+Qwen2-72B-Instruct,0.9612934835864773
+cross_openhermes_llama3_8b_4096_inst,0.8613424791768741
+Meta-Llama-3-8B-Instruct,0.8946594806467418
+Meta-Llama-3.1-70B-Instruct,0.9559039686428221
+Qwen2_5_3B_Instruct,0.9029887310142087
+SeaLLMs-v3-7B-Chat,0.9265066144047036
+Qwen2_5_72B_Instruct,0.9627633512983832
+gemma-2-9b-it,0.9416952474277315
+Meta-Llama-3-70B-Instruct,0.9480646741793238
+Qwen2_5_14B_Instruct,0.9461048505634493
+sg_llama3_8192_8b,0.9103380695737384
+sg_llama3_70b_inst,0.9524742773150416
+gemma-2-2b-it,0.8510534051935326
+llama3-8b-cpt-sea-lionv2-instruct,0.8858402743753062
+Qwen2_5_0_5B_Instruct,0.6526212640862322
+GPT4o_0513,0.9583537481626654
+cross_openhermes_llama3_70b_4096_inst,0.9514943655071043
+cross_openhermes_llama3_8b_4096_2_inst,0.876531112199902
diff --git a/results/dialogue/zero_shot/samsum.csv b/results/dialogue/zero_shot/samsum.csv
index 432ea7efdaa7a932511e6a0f0b394bfd4ea17963..7300b62a8c625095a2272f635af3e403822de0fb 100644
--- a/results/dialogue/zero_shot/samsum.csv
+++ b/results/dialogue/zero_shot/samsum.csv
@@ -1 +1,24 @@
 Model,Average,ROUGE-1,ROUGE-2,ROUGE-L
+Qwen2-7B-Instruct,0.25668781132950264,0.36375948458827556,0.12939804942125302,0.27690589997897935
+Meta-Llama-3.1-8B-Instruct,0.2891505262763006,0.4001228010515775,0.15677431231732958,0.31055446545999466
+Qwen2_5_32B_Instruct,0.2844232627209405,0.3986263552639068,0.14766658533002341,0.3069768475688912
+Qwen2_5_7B_Instruct,0.2987576845890178,0.4163299367235864,0.1599063413842216,0.32003677565924527
+Qwen2_5_1_5B_Instruct,0.2333120091694482,0.34339111721032756,0.10195887716459845,0.25458603313341865
+Qwen2-72B-Instruct,0.2800906719573321,0.3887231369098802,0.15237661526996754,0.29917226369214855
+cross_openhermes_llama3_8b_4096_inst,0.2961783902880866,0.40739117705606903,0.16227160132916457,0.3188723924790264
+Meta-Llama-3-8B-Instruct,0.2846315092346869,0.39397110152251813,0.154320846916639,0.30560257926490364
+Meta-Llama-3.1-70B-Instruct,0.28934874612070227,0.4036295731242805,0.15211190810296196,0.31230475713486433
+Qwen2_5_3B_Instruct,0.26935624341081515,0.380865832002109,0.13872106416227833,0.28848183406805816
+SeaLLMs-v3-7B-Chat,0.2959981719045788,0.4078820748825196,0.16338306782652476,0.316729373004692
+Qwen2_5_72B_Instruct,0.28852247889830335,0.3996215000271418,0.15494490129237035,0.31100103537539775
+gemma-2-9b-it,0.3100514077180449,0.4289412957792292,0.16727050182456474,0.3339424255503407
+Meta-Llama-3-70B-Instruct,0.2893525314227379,0.4030746211134018,0.15236139065578,0.3126215824990321
+Qwen2_5_14B_Instruct,0.2713801253928723,0.3836253496005304,0.13683087953788298,0.2936841470402035
+sg_llama3_8192_8b,0.30740523414540055,0.4199805360695743,0.1701793607165699,0.33205580565005743
+sg_llama3_70b_inst,0.3146051103643872,0.4271361513564755,0.18238925099430264,0.33428992874238356
+gemma-2-2b-it,0.31118787136959813,0.4324251755711466,0.16441328335793207,0.33672515517971563
+llama3-8b-cpt-sea-lionv2-instruct,0.306997595680581,0.4214048099551701,0.1709790451938523,0.3286089318927205
+Qwen2_5_0_5B_Instruct,0.20766179544894214,0.3105872033328297,0.08726222085933319,0.22513596215466355
+GPT4o_0513,0.27736679291505306,0.386750207633093,0.14889081847621596,0.2964593526358502
+cross_openhermes_llama3_70b_4096_inst,0.32140993091581,0.43714768967090817,0.18346420469253946,0.3436178983839823
+cross_openhermes_llama3_8b_4096_2_inst,0.29120862165554934,0.40224666789707636,0.16041490437445552,0.31096429269511605
diff --git a/results/emotion/few_shot/ind_emotion.csv b/results/emotion/few_shot/ind_emotion.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..30a3511380b03883e1df7de609a9bf42d50a253d 100644
--- a/results/emotion/few_shot/ind_emotion.csv
+++ b/results/emotion/few_shot/ind_emotion.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7204545454545455
+Meta-Llama-3-8B,0.4681818181818182
+llama3-8b-cpt-sea-lionv2-base,0.5727272727272728
+Meta-Llama-3.1-8B,0.5318181818181819
diff --git a/results/emotion/few_shot/sst2.csv b/results/emotion/few_shot/sst2.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..30646975a4d1f914d116550aa103e73b386504d4 100644
--- a/results/emotion/few_shot/sst2.csv
+++ b/results/emotion/few_shot/sst2.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.9036697247706422
+Meta-Llama-3-8B,0.7201834862385321
+llama3-8b-cpt-sea-lionv2-base,0.7282110091743119
+Meta-Llama-3.1-8B,0.8222477064220184
diff --git a/results/emotion/zero_shot/ind_emotion.csv b/results/emotion/zero_shot/ind_emotion.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..7dbec7f9215505a6dd9f84ff8585f81c222282c7 100644
--- a/results/emotion/zero_shot/ind_emotion.csv
+++ b/results/emotion/zero_shot/ind_emotion.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.6545454545454545
+Meta-Llama-3.1-8B-Instruct,0.6545454545454545
+Qwen2_5_32B_Instruct,0.6909090909090909
+Qwen2_5_7B_Instruct,0.6636363636363637
+Qwen2_5_1_5B_Instruct,0.5795454545454546
+Qwen2-72B-Instruct,0.675
+cross_openhermes_llama3_8b_4096_inst,0.6704545454545454
+Meta-Llama-3-8B-Instruct,0.6522727272727272
+Meta-Llama-3.1-70B-Instruct,0.7159090909090909
+Qwen2_5_3B_Instruct,0.5522727272727272
+SeaLLMs-v3-7B-Chat,0.6454545454545455
+Qwen2_5_72B_Instruct,0.7068181818181818
+gemma-2-9b-it,0.7477272727272727
+Meta-Llama-3-70B-Instruct,0.6909090909090909
+Qwen2_5_14B_Instruct,0.6954545454545454
+sg_llama3_8192_8b,0.6045454545454545
+sg_llama3_70b_inst,0.7
+gemma-2-2b-it,0.6636363636363637
+llama3-8b-cpt-sea-lionv2-instruct,0.6613636363636364
+Qwen2_5_0_5B_Instruct,0.37727272727272726
+GPT4o_0513,0.7068181818181818
+cross_openhermes_llama3_70b_4096_inst,0.6863636363636364
+cross_openhermes_llama3_8b_4096_2_inst,0.6863636363636364
diff --git a/results/emotion/zero_shot/sst2.csv b/results/emotion/zero_shot/sst2.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..20004e95232fff32719f2455c532ffa7914d60a9 100644
--- a/results/emotion/zero_shot/sst2.csv
+++ b/results/emotion/zero_shot/sst2.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.9346330275229358
+Meta-Llama-3.1-8B-Instruct,0.8646788990825688
+Qwen2_5_32B_Instruct,0.9472477064220184
+Qwen2_5_7B_Instruct,0.9254587155963303
+Qwen2_5_1_5B_Instruct,0.9231651376146789
+Qwen2-72B-Instruct,0.9346330275229358
+cross_openhermes_llama3_8b_4096_inst,0.926605504587156
+Meta-Llama-3-8B-Instruct,0.8784403669724771
+Meta-Llama-3.1-70B-Instruct,0.9529816513761468
+Qwen2_5_3B_Instruct,0.8245412844036697
+SeaLLMs-v3-7B-Chat,0.9403669724770642
+Qwen2_5_72B_Instruct,0.9334862385321101
+gemma-2-9b-it,0.9311926605504587
+Meta-Llama-3-70B-Instruct,0.9495412844036697
+Qwen2_5_14B_Instruct,0.9311926605504587
+sg_llama3_8192_8b,0.9208715596330275
+sg_llama3_70b_inst,0.9334862385321101
+gemma-2-2b-it,0.9243119266055045
+llama3-8b-cpt-sea-lionv2-instruct,0.9128440366972477
+Qwen2_5_0_5B_Instruct,0.7889908256880734
+GPT4o_0513,0.9415137614678899
+cross_openhermes_llama3_70b_4096_inst,0.9380733944954128
+cross_openhermes_llama3_8b_4096_2_inst,0.930045871559633
diff --git a/results/flores_translation/few_shot/ind2eng.csv b/results/flores_translation/few_shot/ind2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..899d1370b188a217e1cdcdc055a8190596c3f321 100644
--- a/results/flores_translation/few_shot/ind2eng.csv
+++ b/results/flores_translation/few_shot/ind2eng.csv
@@ -1 +1,5 @@
 Model,BLEU
+Meta-Llama-3.1-70B,0.42145684080212753
+Meta-Llama-3-8B,0.37684086636912956
+llama3-8b-cpt-sea-lionv2-base,0.38065942591799257
+Meta-Llama-3.1-8B,0.38181303557840174
diff --git a/results/flores_translation/few_shot/vie2eng.csv b/results/flores_translation/few_shot/vie2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..7a823c975f043edecb0a6bc482360ac96d5d6529 100644
--- a/results/flores_translation/few_shot/vie2eng.csv
+++ b/results/flores_translation/few_shot/vie2eng.csv
@@ -1 +1,5 @@
 Model,BLEU
+Meta-Llama-3.1-70B,0.3486043252859807
+Meta-Llama-3-8B,0.3088281924097908
+llama3-8b-cpt-sea-lionv2-base,0.3101352718812011
+Meta-Llama-3.1-8B,0.31860377848723964
diff --git a/results/flores_translation/few_shot/zho2eng.csv b/results/flores_translation/few_shot/zho2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..a02431bc8e6cd248193119fbf668f0a06de9f889 100644
--- a/results/flores_translation/few_shot/zho2eng.csv
+++ b/results/flores_translation/few_shot/zho2eng.csv
@@ -1 +1,5 @@
 Model,BLEU
+Meta-Llama-3.1-70B,0.2784128355061452
+Meta-Llama-3-8B,0.24157503759807666
+llama3-8b-cpt-sea-lionv2-base,0.2196548010627023
+Meta-Llama-3.1-8B,0.23636236548065317
diff --git a/results/flores_translation/few_shot/zsm2eng.csv b/results/flores_translation/few_shot/zsm2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..0d22724602fd412c930906e44f9e9fda8ce19733 100644
--- a/results/flores_translation/few_shot/zsm2eng.csv
+++ b/results/flores_translation/few_shot/zsm2eng.csv
@@ -1 +1,5 @@
 Model,BLEU
+Meta-Llama-3.1-70B,0.4419951682556223
+Meta-Llama-3-8B,0.38778379180318306
+llama3-8b-cpt-sea-lionv2-base,0.373752985045955
+Meta-Llama-3.1-8B,0.39297234157214134
diff --git a/results/flores_translation/zero_shot/ind2eng.csv b/results/flores_translation/zero_shot/ind2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..4111182af55a8368007d63d6e85ed82923d004c8 100644
--- a/results/flores_translation/zero_shot/ind2eng.csv
+++ b/results/flores_translation/zero_shot/ind2eng.csv
@@ -1 +1,20 @@
 Model,BLEU
+Qwen2-7B-Instruct,0.29408553325533265
+Meta-Llama-3.1-8B-Instruct,0.3765752579792989
+Qwen2_5_7B_Instruct,0.36472669481333536
+Qwen2-72B-Instruct,0.4043588265556185
+cross_openhermes_llama3_8b_4096_inst,0.37782883404862155
+Meta-Llama-3-8B-Instruct,0.33079891679041123
+Meta-Llama-3.1-70B-Instruct,0.43366494500251235
+Qwen2_5_3B_Instruct,0.3316936422167389
+SeaLLMs-v3-7B-Chat,0.3594829412574955
+gemma-2-9b-it,0.40786563079141763
+Meta-Llama-3-70B-Instruct,0.3830092775167675
+Qwen2_5_14B_Instruct,0.3901044620348051
+sg_llama3_8192_8b,0.3758986882788705
+sg_llama3_70b_inst,0.4086440304524362
+gemma-2-2b-it,0.3482500758113138
+llama3-8b-cpt-sea-lionv2-instruct,0.3916108972514423
+GPT4o_0513,0.42589589086974855
+cross_openhermes_llama3_70b_4096_inst,0.4206616934730876
+cross_openhermes_llama3_8b_4096_2_inst,0.38791104175399305
diff --git a/results/flores_translation/zero_shot/vie2eng.csv b/results/flores_translation/zero_shot/vie2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..cd8c4024f44cfa1015e1677c0030ccaf27e5dfad 100644
--- a/results/flores_translation/zero_shot/vie2eng.csv
+++ b/results/flores_translation/zero_shot/vie2eng.csv
@@ -1 +1,20 @@
 Model,BLEU
+Qwen2-7B-Instruct,0.24106736560355876
+Meta-Llama-3.1-8B-Instruct,0.31019605539004524
+Qwen2_5_7B_Instruct,0.3027564749728372
+Qwen2-72B-Instruct,0.33005323227052946
+cross_openhermes_llama3_8b_4096_inst,0.28905588559612455
+Meta-Llama-3-8B-Instruct,0.2647448190950291
+Meta-Llama-3.1-70B-Instruct,0.37244508311079816
+Qwen2_5_3B_Instruct,0.27312609009801636
+SeaLLMs-v3-7B-Chat,0.30981028289420137
+gemma-2-9b-it,0.3367700653885
+Meta-Llama-3-70B-Instruct,0.3230140263371192
+Qwen2_5_14B_Instruct,0.32198218156960645
+sg_llama3_8192_8b,0.3087032778607667
+sg_llama3_70b_inst,0.34258533717783785
+gemma-2-2b-it,0.27518909199172303
+llama3-8b-cpt-sea-lionv2-instruct,0.327781936019637
+GPT4o_0513,0.36219303373759176
+cross_openhermes_llama3_70b_4096_inst,0.3538368711937718
+cross_openhermes_llama3_8b_4096_2_inst,0.2995657605717809
diff --git a/results/flores_translation/zero_shot/zho2eng.csv b/results/flores_translation/zero_shot/zho2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..9aaf1c380c85c89845f315c280325a5d3cc64d5c 100644
--- a/results/flores_translation/zero_shot/zho2eng.csv
+++ b/results/flores_translation/zero_shot/zho2eng.csv
@@ -1 +1,20 @@
 Model,BLEU
+Qwen2-7B-Instruct,0.2113761361724575
+Meta-Llama-3.1-8B-Instruct,0.23889886925287113
+Qwen2_5_7B_Instruct,0.2437311220019033
+Qwen2-72B-Instruct,0.23893268538329387
+cross_openhermes_llama3_8b_4096_inst,0.2258901846942186
+Meta-Llama-3-8B-Instruct,0.199495011482748
+Meta-Llama-3.1-70B-Instruct,0.2832594176173152
+Qwen2_5_3B_Instruct,0.2245195134637718
+SeaLLMs-v3-7B-Chat,0.2516593644617717
+gemma-2-9b-it,0.267527968123433
+Meta-Llama-3-70B-Instruct,0.24397819518058994
+Qwen2_5_14B_Instruct,0.2627781200417998
+sg_llama3_8192_8b,0.23778397807613597
+sg_llama3_70b_inst,0.26000707510414633
+gemma-2-2b-it,0.21164036008441425
+llama3-8b-cpt-sea-lionv2-instruct,0.2381535278220489
+GPT4o_0513,0.27722306559544163
+cross_openhermes_llama3_70b_4096_inst,0.27230844604661014
+cross_openhermes_llama3_8b_4096_2_inst,0.24086384403666913
diff --git a/results/flores_translation/zero_shot/zsm2eng.csv b/results/flores_translation/zero_shot/zsm2eng.csv
index c92cc58bffcf5c69f0b19b68264727e785b847ae..35a6c296cbdc0716b919f7aa4df01e50ba35ed00 100644
--- a/results/flores_translation/zero_shot/zsm2eng.csv
+++ b/results/flores_translation/zero_shot/zsm2eng.csv
@@ -1 +1,20 @@
 Model,BLEU
+Qwen2-7B-Instruct,0.28031997065822994
+Meta-Llama-3.1-8B-Instruct,0.3700921225177551
+Qwen2_5_7B_Instruct,0.3466422765302921
+Qwen2-72B-Instruct,0.40796892621611885
+cross_openhermes_llama3_8b_4096_inst,0.37996622288549425
+Meta-Llama-3-8B-Instruct,0.31625368345049
+Meta-Llama-3.1-70B-Instruct,0.4462132282683508
+Qwen2_5_3B_Instruct,0.31056841204320457
+SeaLLMs-v3-7B-Chat,0.3484133510670942
+gemma-2-9b-it,0.4234100394581857
+Meta-Llama-3-70B-Instruct,0.3957287030176054
+Qwen2_5_14B_Instruct,0.3841042767934729
+sg_llama3_8192_8b,0.376818225699898
+sg_llama3_70b_inst,0.4163761508073963
+gemma-2-2b-it,0.33737270487369614
+llama3-8b-cpt-sea-lionv2-instruct,0.38799258214381604
+GPT4o_0513,0.451496635720668
+cross_openhermes_llama3_70b_4096_inst,0.43447247409976697
+cross_openhermes_llama3_8b_4096_2_inst,0.3909715760518667
diff --git a/results/fundamental_nlp_tasks/few_shot/c3.csv b/results/fundamental_nlp_tasks/few_shot/c3.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..1d8edfe3686f4eced58da04abea262934d211e2c 100644
--- a/results/fundamental_nlp_tasks/few_shot/c3.csv
+++ b/results/fundamental_nlp_tasks/few_shot/c3.csv
@@ -1 +1,4 @@
 Model,Accuracy
+Meta-Llama-3-8B,0.7655198204936425
+llama3-8b-cpt-sea-lionv2-base,0.7995512341062079
+Meta-Llama-3.1-8B,0.8103964098728497
diff --git a/results/fundamental_nlp_tasks/few_shot/cola.csv b/results/fundamental_nlp_tasks/few_shot/cola.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..f6a4095a2633c334a3299bb38081b5458fc7d0c8 100644
--- a/results/fundamental_nlp_tasks/few_shot/cola.csv
+++ b/results/fundamental_nlp_tasks/few_shot/cola.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7248322147651006
+Meta-Llama-3-8B,0.5934803451581975
+llama3-8b-cpt-sea-lionv2-base,0.6203259827420902
+Meta-Llama-3.1-8B,0.6471716203259827
diff --git a/results/fundamental_nlp_tasks/few_shot/mnli.csv b/results/fundamental_nlp_tasks/few_shot/mnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..4dd57d0a9e9aabb2df8dda802a752667efa328ea 100644
--- a/results/fundamental_nlp_tasks/few_shot/mnli.csv
+++ b/results/fundamental_nlp_tasks/few_shot/mnli.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7395
+Meta-Llama-3-8B,0.442
+llama3-8b-cpt-sea-lionv2-base,0.456
+Meta-Llama-3.1-8B,0.465
diff --git a/results/fundamental_nlp_tasks/few_shot/mrpc.csv b/results/fundamental_nlp_tasks/few_shot/mrpc.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..2481c0c4f7879200d8f14520e0e37597cf0a7008 100644
--- a/results/fundamental_nlp_tasks/few_shot/mrpc.csv
+++ b/results/fundamental_nlp_tasks/few_shot/mrpc.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.6397058823529411
+Meta-Llama-3-8B,0.5906862745098039
+llama3-8b-cpt-sea-lionv2-base,0.5686274509803921
+Meta-Llama-3.1-8B,0.571078431372549
diff --git a/results/fundamental_nlp_tasks/few_shot/ocnli.csv b/results/fundamental_nlp_tasks/few_shot/ocnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..eb484ed4d465e6fde0a619e2f178e009155ba854 100644
--- a/results/fundamental_nlp_tasks/few_shot/ocnli.csv
+++ b/results/fundamental_nlp_tasks/few_shot/ocnli.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.6786440677966101
+Meta-Llama-3-8B,0.38101694915254236
+llama3-8b-cpt-sea-lionv2-base,0.3871186440677966
+Meta-Llama-3.1-8B,0.4067796610169492
diff --git a/results/fundamental_nlp_tasks/few_shot/qnli.csv b/results/fundamental_nlp_tasks/few_shot/qnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..44a262af8c3e3b98b147607c39910afdca0bb326 100644
--- a/results/fundamental_nlp_tasks/few_shot/qnli.csv
+++ b/results/fundamental_nlp_tasks/few_shot/qnli.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.5777045579352005
+Meta-Llama-3-8B,0.5028372688998719
+llama3-8b-cpt-sea-lionv2-base,0.500274574409665
+Meta-Llama-3.1-8B,0.500274574409665
diff --git a/results/fundamental_nlp_tasks/few_shot/qqp.csv b/results/fundamental_nlp_tasks/few_shot/qqp.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..9e51863e34df728d9bf5a0bc7f6a47d50c9ef0bb 100644
--- a/results/fundamental_nlp_tasks/few_shot/qqp.csv
+++ b/results/fundamental_nlp_tasks/few_shot/qqp.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7365
+Meta-Llama-3-8B,0.54
+llama3-8b-cpt-sea-lionv2-base,0.5295
+Meta-Llama-3.1-8B,0.557
diff --git a/results/fundamental_nlp_tasks/few_shot/rte.csv b/results/fundamental_nlp_tasks/few_shot/rte.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..eb2060cdc0862caee2c43a2cb93d6472027166c7 100644
--- a/results/fundamental_nlp_tasks/few_shot/rte.csv
+++ b/results/fundamental_nlp_tasks/few_shot/rte.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7725631768953068
+Meta-Llama-3-8B,0.5848375451263538
+llama3-8b-cpt-sea-lionv2-base,0.6570397111913358
+Meta-Llama-3.1-8B,0.6642599277978339
diff --git a/results/fundamental_nlp_tasks/few_shot/wnli.csv b/results/fundamental_nlp_tasks/few_shot/wnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..6a308b29dc8d4dbdd28946a716cdbc379c762045 100644
--- a/results/fundamental_nlp_tasks/few_shot/wnli.csv
+++ b/results/fundamental_nlp_tasks/few_shot/wnli.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7323943661971831
+Meta-Llama-3-8B,0.49295774647887325
+llama3-8b-cpt-sea-lionv2-base,0.43661971830985913
+Meta-Llama-3.1-8B,0.5774647887323944
diff --git a/results/fundamental_nlp_tasks/zero_shot/c3.csv b/results/fundamental_nlp_tasks/zero_shot/c3.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..c8874c0921eba93bf0e9615929bbcfb9ea0f4578 100644
--- a/results/fundamental_nlp_tasks/zero_shot/c3.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/c3.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.9244577412116679
+Meta-Llama-3.1-8B-Instruct,0.8672400897531788
+Qwen2_5_32B_Instruct,0.9603590127150337
+Qwen2_5_7B_Instruct,0.9121166791323859
+Qwen2_5_1_5B_Instruct,0.793941660433807
+Qwen2-72B-Instruct,0.9611069558713538
+cross_openhermes_llama3_8b_4096_inst,0.7718773373223635
+Meta-Llama-3-8B-Instruct,0.8515332834704562
+Meta-Llama-3.1-70B-Instruct,0.9603590127150337
+Qwen2_5_3B_Instruct,0.8668661181750187
+SeaLLMs-v3-7B-Chat,0.9143605086013463
+Qwen2_5_72B_Instruct,0.9596110695587136
+gemma-2-9b-it,0.9222139117427075
+Meta-Llama-3-70B-Instruct,0.9521316379955124
+Qwen2_5_14B_Instruct,0.9502617801047121
+sg_llama3_8192_8b,0.8051608077786089
+sg_llama3_70b_inst,0.9289454001495886
+gemma-2-2b-it,0.7700074794315632
+llama3-8b-cpt-sea-lionv2-instruct,0.8672400897531788
+Qwen2_5_0_5B_Instruct,0.612939416604338
+GPT4o_0513,0.9648466716529543
+cross_openhermes_llama3_70b_4096_inst,0.9270755422587883
+cross_openhermes_llama3_8b_4096_2_inst,0.8290949887808526
diff --git a/results/fundamental_nlp_tasks/zero_shot/cola.csv b/results/fundamental_nlp_tasks/zero_shot/cola.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..d8c9e9455d289badfbff2af4cd4eb8a098cbcd77 100644
--- a/results/fundamental_nlp_tasks/zero_shot/cola.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/cola.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7871524448705657
+Meta-Llama-3.1-8B-Instruct,0.6673058485139022
+Qwen2_5_32B_Instruct,0.8427612655800575
+Qwen2_5_7B_Instruct,0.7909875359539789
+Qwen2_5_1_5B_Instruct,0.7497603068072867
+Qwen2-72B-Instruct,0.8341323106423778
+cross_openhermes_llama3_8b_4096_inst,0.7660594439117929
+Meta-Llama-3-8B-Instruct,0.6548418024928092
+Meta-Llama-3.1-70B-Instruct,0.850431447746884
+Qwen2_5_3B_Instruct,0.6644295302013423
+SeaLLMs-v3-7B-Chat,0.785234899328859
+Qwen2_5_72B_Instruct,0.8571428571428571
+gemma-2-9b-it,0.7938638542665388
+Meta-Llama-3-70B-Instruct,0.835091083413231
+Qwen2_5_14B_Instruct,0.8063279002876318
+sg_llama3_8192_8b,0.8130393096836049
+sg_llama3_70b_inst,0.8696069031639502
+gemma-2-2b-it,0.6749760306807286
+llama3-8b-cpt-sea-lionv2-instruct,0.6078619367209971
+Qwen2_5_0_5B_Instruct,0.6116970278044104
+GPT4o_0513,0.8398849472674976
+cross_openhermes_llama3_70b_4096_inst,0.8456375838926175
+cross_openhermes_llama3_8b_4096_2_inst,0.7651006711409396
diff --git a/results/fundamental_nlp_tasks/zero_shot/mnli.csv b/results/fundamental_nlp_tasks/zero_shot/mnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..b910200fcf592900695fb4e355b00b93f8bc8bec 100644
--- a/results/fundamental_nlp_tasks/zero_shot/mnli.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/mnli.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7295
+Meta-Llama-3.1-8B-Instruct,0.4825
+Qwen2_5_32B_Instruct,0.8715
+Qwen2_5_7B_Instruct,0.8105
+Qwen2_5_1_5B_Instruct,0.6045
+Qwen2-72B-Instruct,0.7925
+cross_openhermes_llama3_8b_4096_inst,0.57
+Meta-Llama-3-8B-Instruct,0.546
+Meta-Llama-3.1-70B-Instruct,0.7015
+Qwen2_5_3B_Instruct,0.7465
+SeaLLMs-v3-7B-Chat,0.653
+Qwen2_5_72B_Instruct,0.8445
+gemma-2-9b-it,0.716
+Meta-Llama-3-70B-Instruct,0.6709421285692472
+Qwen2_5_14B_Instruct,0.818
+sg_llama3_8192_8b,0.6605
+sg_llama3_70b_inst,0.7685
+gemma-2-2b-it,0.6185
+llama3-8b-cpt-sea-lionv2-instruct,0.5765
+Qwen2_5_0_5B_Instruct,0.5095
+GPT4o_0513,0.8335
+cross_openhermes_llama3_70b_4096_inst,0.743
+cross_openhermes_llama3_8b_4096_2_inst,0.619
diff --git a/results/fundamental_nlp_tasks/zero_shot/mrpc.csv b/results/fundamental_nlp_tasks/zero_shot/mrpc.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..fafc902b77eacf66b4953d126621b128fa9c9a01 100644
--- a/results/fundamental_nlp_tasks/zero_shot/mrpc.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/mrpc.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7867647058823529
+Meta-Llama-3.1-8B-Instruct,0.6740196078431373
+Qwen2_5_32B_Instruct,0.7745098039215687
+Qwen2_5_7B_Instruct,0.7058823529411765
+Qwen2_5_1_5B_Instruct,0.6838235294117647
+Qwen2-72B-Instruct,0.8063725490196079
+cross_openhermes_llama3_8b_4096_inst,0.7303921568627451
+Meta-Llama-3-8B-Instruct,0.678921568627451
+Meta-Llama-3.1-70B-Instruct,0.7696078431372549
+Qwen2_5_3B_Instruct,0.5661764705882353
+SeaLLMs-v3-7B-Chat,0.7475490196078431
+Qwen2_5_72B_Instruct,0.8014705882352942
+gemma-2-9b-it,0.7401960784313726
+Meta-Llama-3-70B-Instruct,0.7598039215686274
+Qwen2_5_14B_Instruct,0.7794117647058824
+sg_llama3_8192_8b,0.7254901960784313
+sg_llama3_70b_inst,0.7892156862745098
+gemma-2-2b-it,0.7083333333333334
+llama3-8b-cpt-sea-lionv2-instruct,0.5833333333333334
+Qwen2_5_0_5B_Instruct,0.5759803921568627
+GPT4o_0513,0.7377450980392157
+cross_openhermes_llama3_70b_4096_inst,0.7818627450980392
+cross_openhermes_llama3_8b_4096_2_inst,0.6985294117647058
diff --git a/results/fundamental_nlp_tasks/zero_shot/ocnli.csv b/results/fundamental_nlp_tasks/zero_shot/ocnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..7f94c1e78aaa6f1348305bc6f62bf05f0154cfdf 100644
--- a/results/fundamental_nlp_tasks/zero_shot/ocnli.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/ocnli.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.6542372881355932
+Meta-Llama-3.1-8B-Instruct,0.40983050847457625
+Qwen2_5_32B_Instruct,0.7742372881355932
+Qwen2_5_7B_Instruct,0.6732203389830509
+Qwen2_5_1_5B_Instruct,0.5135593220338983
+Qwen2-72B-Instruct,0.7820338983050847
+cross_openhermes_llama3_8b_4096_inst,0.5183050847457628
+Meta-Llama-3-8B-Instruct,0.44033898305084745
+Meta-Llama-3.1-70B-Instruct,0.6423728813559322
+Qwen2_5_3B_Instruct,0.6145762711864406
+SeaLLMs-v3-7B-Chat,0.5698305084745763
+Qwen2_5_72B_Instruct,0.7684745762711864
+gemma-2-9b-it,0.6189830508474576
+Meta-Llama-3-70B-Instruct,0.5928813559322034
+Qwen2_5_14B_Instruct,0.7538983050847458
+sg_llama3_8192_8b,0.5084745762711864
+sg_llama3_70b_inst,0.6420338983050847
+gemma-2-2b-it,0.43322033898305085
+llama3-8b-cpt-sea-lionv2-instruct,0.45559322033898303
+Qwen2_5_0_5B_Instruct,0.3847457627118644
+GPT4o_0513,0.7308474576271187
+cross_openhermes_llama3_70b_4096_inst,0.6647457627118644
+cross_openhermes_llama3_8b_4096_2_inst,0.5498305084745763
diff --git a/results/fundamental_nlp_tasks/zero_shot/qnli.csv b/results/fundamental_nlp_tasks/zero_shot/qnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..0aff80d2f68bf99fdc55421cc8417cd478494800 100644
--- a/results/fundamental_nlp_tasks/zero_shot/qnli.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/qnli.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.8154859967051071
+Meta-Llama-3.1-8B-Instruct,0.5777045579352005
+Qwen2_5_32B_Instruct,0.9062786015010068
+Qwen2_5_7B_Instruct,0.8652754896576972
+Qwen2_5_1_5B_Instruct,0.6148636280431997
+Qwen2-72B-Instruct,0.8887058392824455
+cross_openhermes_llama3_8b_4096_inst,0.7596558667398865
+Meta-Llama-3-8B-Instruct,0.6025993044114956
+Meta-Llama-3.1-70B-Instruct,0.9026176093721399
+Qwen2_5_3B_Instruct,0.7645982061138569
+SeaLLMs-v3-7B-Chat,0.7159070107999268
+Qwen2_5_72B_Instruct,0.9082921471718836
+gemma-2-9b-it,0.9070107999267801
+Meta-Llama-3-70B-Instruct,0.876807614863628
+Qwen2_5_14B_Instruct,0.9079260479589969
+sg_llama3_8192_8b,0.8118250045762402
+sg_llama3_70b_inst,0.9004210140948197
+gemma-2-2b-it,0.7792421746293245
+llama3-8b-cpt-sea-lionv2-instruct,0.6101043382756727
+Qwen2_5_0_5B_Instruct,0.5464030752333883
+GPT4o_0513,0.9304411495515285
+cross_openhermes_llama3_70b_4096_inst,0.8943803770821893
+cross_openhermes_llama3_8b_4096_2_inst,0.7971810360607725
diff --git a/results/fundamental_nlp_tasks/zero_shot/qqp.csv b/results/fundamental_nlp_tasks/zero_shot/qqp.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..5f16c85d373ee7cbc3f54428938cf79c5523630f 100644
--- a/results/fundamental_nlp_tasks/zero_shot/qqp.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/qqp.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.781
+Meta-Llama-3.1-8B-Instruct,0.5645
+Qwen2_5_32B_Instruct,0.8315
+Qwen2_5_7B_Instruct,0.76
+Qwen2_5_1_5B_Instruct,0.731
+Qwen2-72B-Instruct,0.8065
+cross_openhermes_llama3_8b_4096_inst,0.7495
+Meta-Llama-3-8B-Instruct,0.563
+Meta-Llama-3.1-70B-Instruct,0.815
+Qwen2_5_3B_Instruct,0.7415
+SeaLLMs-v3-7B-Chat,0.7625
+Qwen2_5_72B_Instruct,0.8315
+gemma-2-9b-it,0.7775
+Meta-Llama-3-70B-Instruct,0.7876082117239673
+Qwen2_5_14B_Instruct,0.8255
+sg_llama3_8192_8b,0.8095
+sg_llama3_70b_inst,0.804
+gemma-2-2b-it,0.761
+llama3-8b-cpt-sea-lionv2-instruct,0.6225
+Qwen2_5_0_5B_Instruct,0.619
+GPT4o_0513,0.8085
+cross_openhermes_llama3_70b_4096_inst,0.801
+cross_openhermes_llama3_8b_4096_2_inst,0.79
diff --git a/results/fundamental_nlp_tasks/zero_shot/rte.csv b/results/fundamental_nlp_tasks/zero_shot/rte.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..6b1227df16a7c693b7d464c3bf202d56237122b5 100644
--- a/results/fundamental_nlp_tasks/zero_shot/rte.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/rte.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.8231046931407943
+Meta-Llama-3.1-8B-Instruct,0.6750902527075813
+Qwen2_5_32B_Instruct,0.9097472924187726
+Qwen2_5_7B_Instruct,0.8592057761732852
+Qwen2_5_1_5B_Instruct,0.703971119133574
+Qwen2-72B-Instruct,0.8447653429602888
+cross_openhermes_llama3_8b_4096_inst,0.6967509025270758
+Meta-Llama-3-8B-Instruct,0.6173285198555957
+Meta-Llama-3.1-70B-Instruct,0.8483754512635379
+Qwen2_5_3B_Instruct,0.779783393501805
+SeaLLMs-v3-7B-Chat,0.7870036101083032
+Qwen2_5_72B_Instruct,0.9025270758122743
+gemma-2-9b-it,0.7472924187725631
+Meta-Llama-3-70B-Instruct,0.8086642599277978
+Qwen2_5_14B_Instruct,0.8664259927797834
+sg_llama3_8192_8b,0.7364620938628159
+sg_llama3_70b_inst,0.8916967509025271
+gemma-2-2b-it,0.7292418772563177
+llama3-8b-cpt-sea-lionv2-instruct,0.6859205776173285
+Qwen2_5_0_5B_Instruct,0.5992779783393501
+GPT4o_0513,0.8700361010830325
+cross_openhermes_llama3_70b_4096_inst,0.8953068592057761
+cross_openhermes_llama3_8b_4096_2_inst,0.7545126353790613
diff --git a/results/fundamental_nlp_tasks/zero_shot/wnli.csv b/results/fundamental_nlp_tasks/zero_shot/wnli.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..f0e0b69107ddbaeec7446917a395231763863530 100644
--- a/results/fundamental_nlp_tasks/zero_shot/wnli.csv
+++ b/results/fundamental_nlp_tasks/zero_shot/wnli.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7183098591549296
+Meta-Llama-3.1-8B-Instruct,0.49295774647887325
+Qwen2_5_32B_Instruct,0.8732394366197183
+Qwen2_5_7B_Instruct,0.7605633802816901
+Qwen2_5_1_5B_Instruct,0.4647887323943662
+Qwen2-72B-Instruct,0.8873239436619719
+cross_openhermes_llama3_8b_4096_inst,0.4647887323943662
+Meta-Llama-3-8B-Instruct,0.4788732394366197
+Meta-Llama-3.1-70B-Instruct,0.8450704225352113
+Qwen2_5_3B_Instruct,0.647887323943662
+SeaLLMs-v3-7B-Chat,0.5915492957746479
+Qwen2_5_72B_Instruct,0.8169014084507042
+gemma-2-9b-it,0.7746478873239436
+Meta-Llama-3-70B-Instruct,0.7887323943661971
+Qwen2_5_14B_Instruct,0.8309859154929577
+sg_llama3_8192_8b,0.704225352112676
+sg_llama3_70b_inst,0.8309859154929577
+gemma-2-2b-it,0.43661971830985913
+llama3-8b-cpt-sea-lionv2-instruct,0.5774647887323944
+Qwen2_5_0_5B_Instruct,0.43661971830985913
+GPT4o_0513,0.9295774647887324
+cross_openhermes_llama3_70b_4096_inst,0.8450704225352113
+cross_openhermes_llama3_8b_4096_2_inst,0.43661971830985913
diff --git a/results/general_reasoning/few_shot/c_eval.csv b/results/general_reasoning/few_shot/c_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..12e0768b6b102f57b50dc039c72623d2fd5f29a7 100644
--- a/results/general_reasoning/few_shot/c_eval.csv
+++ b/results/general_reasoning/few_shot/c_eval.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.6363636363636364
+Meta-Llama-3-8B,0.43212951432129515
+llama3-8b-cpt-sea-lionv2-base,0.40099626400996263
+Meta-Llama-3.1-8B,0.43711083437110837
diff --git a/results/general_reasoning/few_shot/cmmlu.csv b/results/general_reasoning/few_shot/cmmlu.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..94b0cf4c8eab647bb20a0b0a063554def9c7a64d 100644
--- a/results/general_reasoning/few_shot/cmmlu.csv
+++ b/results/general_reasoning/few_shot/cmmlu.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.6496287342427906
+Meta-Llama-3-8B,0.4393023657399413
+llama3-8b-cpt-sea-lionv2-base,0.4429286824382663
+Meta-Llama-3.1-8B,0.45467104127093766
diff --git a/results/general_reasoning/few_shot/indommlu.csv b/results/general_reasoning/few_shot/indommlu.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..4c3c2db7f3249e40a459319d5a493b201909eadc 100644
--- a/results/general_reasoning/few_shot/indommlu.csv
+++ b/results/general_reasoning/few_shot/indommlu.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.6336204018959877
+Meta-Llama-3-8B,0.4515655250684291
+llama3-8b-cpt-sea-lionv2-base,0.5042392683089659
+Meta-Llama-3.1-8B,0.47393016890313105
diff --git a/results/general_reasoning/few_shot/mmlu.csv b/results/general_reasoning/few_shot/mmlu.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..e01b2482f1e6c2f778e47dd1bca1619de54f1992 100644
--- a/results/general_reasoning/few_shot/mmlu.csv
+++ b/results/general_reasoning/few_shot/mmlu.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.7457275652484805
+Meta-Llama-3-8B,0.5681086878798713
+llama3-8b-cpt-sea-lionv2-base,0.5608866642831605
+Meta-Llama-3.1-8B,0.5723274937432964
diff --git a/results/general_reasoning/few_shot/zbench.csv b/results/general_reasoning/few_shot/zbench.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..54824c3ad624bf80a4e574d55e19ccbc29c8b25c 100644
--- a/results/general_reasoning/few_shot/zbench.csv
+++ b/results/general_reasoning/few_shot/zbench.csv
@@ -1 +1,5 @@
 Model,Accuracy
+Meta-Llama-3.1-70B,0.5757575757575758
+Meta-Llama-3-8B,0.24242424242424243
+llama3-8b-cpt-sea-lionv2-base,0.2727272727272727
+Meta-Llama-3.1-8B,0.3939393939393939
diff --git a/results/general_reasoning/zero_shot/c_eval.csv b/results/general_reasoning/zero_shot/c_eval.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..b012a69cf6395b3c5fc7a0cc21ef30c73bc375e0 100644
--- a/results/general_reasoning/zero_shot/c_eval.csv
+++ b/results/general_reasoning/zero_shot/c_eval.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7615193026151931
+Meta-Llama-3.1-8B-Instruct,0.5149439601494396
+Qwen2_5_32B_Instruct,0.8262764632627646
+Qwen2_5_7B_Instruct,0.7459526774595268
+Qwen2_5_1_5B_Instruct,0.5971357409713575
+Qwen2-72B-Instruct,0.8312577833125778
+cross_openhermes_llama3_8b_4096_inst,0.44707347447073476
+Meta-Llama-3-8B-Instruct,0.4775840597758406
+Meta-Llama-3.1-70B-Instruct,0.6612702366127023
+Qwen2_5_3B_Instruct,0.6537982565379825
+SeaLLMs-v3-7B-Chat,0.7658779576587795
+Qwen2_5_72B_Instruct,0.8325031133250311
+gemma-2-9b-it,0.5523038605230386
+Meta-Llama-3-70B-Instruct,0.6220423412204235
+Qwen2_5_14B_Instruct,0.7839352428393525
+sg_llama3_8192_8b,0.4825653798256538
+sg_llama3_70b_inst,0.5722291407222914
+gemma-2-2b-it,0.4352428393524284
+llama3-8b-cpt-sea-lionv2-instruct,0.49813200498132004
+Qwen2_5_0_5B_Instruct,0.41718555417185554
+GPT4o_0513,0.7073474470734745
+cross_openhermes_llama3_70b_4096_inst,0.5734744707347447
+cross_openhermes_llama3_8b_4096_2_inst,0.4738480697384807
diff --git a/results/general_reasoning/zero_shot/cmmlu.csv b/results/general_reasoning/zero_shot/cmmlu.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..3abc2320c91b2bb7d40317d5d6bb4b599f271880 100644
--- a/results/general_reasoning/zero_shot/cmmlu.csv
+++ b/results/general_reasoning/zero_shot/cmmlu.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7727508202383008
+Meta-Llama-3.1-8B-Instruct,0.5246934898981178
+Qwen2_5_32B_Instruct,0.8273182524607149
+Qwen2_5_7B_Instruct,0.7486617164565705
+Qwen2_5_1_5B_Instruct,0.5975651873596961
+Qwen2-72B-Instruct,0.8293904334311863
+cross_openhermes_llama3_8b_4096_inst,0.4547573821447073
+Meta-Llama-3-8B-Instruct,0.4839405974788465
+Meta-Llama-3.1-70B-Instruct,0.6814885166637886
+Qwen2_5_3B_Instruct,0.6621481609393887
+SeaLLMs-v3-7B-Chat,0.7684337765498187
+Qwen2_5_72B_Instruct,0.8343982041098256
+gemma-2-9b-it,0.5700224486271801
+Meta-Llama-3-70B-Instruct,0.6494560524952513
+Qwen2_5_14B_Instruct,0.7807805214988776
+sg_llama3_8192_8b,0.49050250388533934
+sg_llama3_70b_inst,0.6044724572612675
+gemma-2-2b-it,0.4412882058366431
+llama3-8b-cpt-sea-lionv2-instruct,0.48929373165256435
+Qwen2_5_0_5B_Instruct,0.42056639613192887
+GPT4o_0513,0.7414954239336902
+cross_openhermes_llama3_70b_4096_inst,0.6177689518217925
+cross_openhermes_llama3_8b_4096_2_inst,0.4807459851493697
diff --git a/results/general_reasoning/zero_shot/indommlu.csv b/results/general_reasoning/zero_shot/indommlu.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..6fd820479a5ff1e0b69a13b768bdaf93c4279293 100644
--- a/results/general_reasoning/zero_shot/indommlu.csv
+++ b/results/general_reasoning/zero_shot/indommlu.csv
@@ -1 +1,24 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.5385539755657921
+Meta-Llama-3.1-8B-Instruct,0.5252687095266707
+Qwen2_5_32B_Instruct,0.6314840777087923
+Qwen2_5_7B_Instruct,0.5600507376994459
+Qwen2_5_1_5B_Instruct,0.4295346818879765
+Qwen2-72B-Instruct,0.6385606515788771
+cross_openhermes_llama3_8b_4096_inst,0.5097803591695039
+Meta-Llama-3-8B-Instruct,0.5264703918819681
+Meta-Llama-3.1-70B-Instruct,0.6740770411910008
+Qwen2_5_3B_Instruct,0.49656185326123237
+SeaLLMs-v3-7B-Chat,0.5267374324053675
+Qwen2_5_72B_Instruct,0.6380933306629281
+gemma-2-9b-it,0.606983109686895
+Meta-Llama-3-70B-Instruct,0.6323519594098405
+Qwen2_5_14B_Instruct,0.6009746979104079
+sg_llama3_8192_8b,0.5021697042526203
+sg_llama3_70b_inst,0.6394285332799252
+gemma-2-2b-it,0.48220842512851325
+llama3-8b-cpt-sea-lionv2-instruct,0.5252687095266707
+Qwen2_5_0_5B_Instruct,0.3279925228653448
+GPT4o_0513,0.7584618465852193
+cross_openhermes_llama3_70b_4096_inst,0.6333533613725882
+cross_openhermes_llama3_8b_4096_2_inst,0.5434942252486815
diff --git a/results/general_reasoning/zero_shot/mmlu.csv b/results/general_reasoning/zero_shot/mmlu.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..2d5abcdb968a87a383601796a1bb68c3e7b6420f 100644
--- a/results/general_reasoning/zero_shot/mmlu.csv
+++ b/results/general_reasoning/zero_shot/mmlu.csv
@@ -1 +1,28 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.672506256703611
+Meta-Llama-3.1-8B-Instruct,0.6037182695745441
+Qwen2_5_32B_Instruct,0.7996424740793707
+Qwen2_5_7B_Instruct,0.6935287808366106
+Qwen2_5_1_5B_Instruct,0.5646764390418305
+Qwen2-72B-Instruct,0.7922774401144083
+cross_openhermes_llama3_8b_4096_inst,0.556381837683232
+Meta-Llama-3-8B-Instruct,0.6005720414730068
+Meta-Llama-3.1-70B-Instruct,0.8058634250983197
+sg_llama3_8192_8b_np,0.6528423310690025
+Qwen2_5_3B_Instruct,0.6118698605648909
+Meta-Llama-3-8B-Instruct_np,0.6619949946371112
+SeaLLMs-v3-7B-Chat,0.6670003575259207
+Qwen2_5_72B_Instruct,0.8129424383267787
+cross_openhermes_llama3_8b_4096_inst_np,0.5601001072577761
+gemma-2-9b-it,0.7100464783696818
+Meta-Llama-3-70B-Instruct,0.7649624597783339
+Qwen2_5_14B_Instruct,0.7542366821594566
+sg_llama3_8192_8b,0.6235967107615302
+sg_llama3_70b_inst,0.7407937075437969
+gemma-2-2b-it,0.5706828745084018
+llama3-8b-cpt-sea-lionv2-instruct,0.6130854486950303
+Qwen2_5_0_5B_Instruct,0.461136932427601
+GPT4o_0513,0.8308187343582409
+llama3-8b-cpt-sea-lionv2-instruct_np,0.6518412584912406
+cross_openhermes_llama3_70b_4096_inst,0.7400071505184126
+cross_openhermes_llama3_8b_4096_2_inst,0.5785484447622453
diff --git a/results/general_reasoning/zero_shot/zbench.csv b/results/general_reasoning/zero_shot/zbench.csv
index 1dd9db3171b0ad2e4edc84dcebb54f8d76c675ab..f042a35bd50d56402c3f365284ee0711ab836a77 100644
--- a/results/general_reasoning/zero_shot/zbench.csv
+++ b/results/general_reasoning/zero_shot/zbench.csv
@@ -1 +1,23 @@
 Model,Accuracy
+Qwen2-7B-Instruct,0.7272727272727273
+Meta-Llama-3.1-8B-Instruct,0.42424242424242425
+Qwen2_5_32B_Instruct,0.6060606060606061
+Qwen2_5_7B_Instruct,0.6666666666666666
+Qwen2_5_1_5B_Instruct,0.42424242424242425
+Qwen2-72B-Instruct,0.5757575757575758
+cross_openhermes_llama3_8b_4096_inst,0.3333333333333333
+Meta-Llama-3-8B-Instruct,0.3333333333333333
+Meta-Llama-3.1-70B-Instruct,0.48484848484848486
+Qwen2_5_3B_Instruct,0.5757575757575758
+SeaLLMs-v3-7B-Chat,0.5454545454545454
+Qwen2_5_72B_Instruct,0.696969696969697
+gemma-2-9b-it,0.48484848484848486
+Meta-Llama-3-70B-Instruct,0.5151515151515151
+Qwen2_5_14B_Instruct,0.6666666666666666
+sg_llama3_8192_8b,0.30303030303030304
+sg_llama3_70b_inst,0.42424242424242425
+gemma-2-2b-it,0.24242424242424243
+llama3-8b-cpt-sea-lionv2-instruct,0.30303030303030304
+Qwen2_5_0_5B_Instruct,0.36363636363636365
+cross_openhermes_llama3_70b_4096_inst,0.42424242424242425
+cross_openhermes_llama3_8b_4096_2_inst,0.45454545454545453