Upload folder using huggingface_hub

results/cross_lingual/zero_shot/cross_logiqa.csv

@@ -1,12 +1,14 @@
 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
+Meta-Llama-3.1-8B-Instruct,0.4862012987012987,0.45876623376623393,0.47208550763939805,0.5909090909090909,0.4715909090909091,0.48863636363636365,0.5340909090909091,0.45454545454545453,0.44886363636363635,0.4147727272727273
 llama3-8b-cpt-sea-lionv2.1-instruct,0.49918831168831174,0.45974025974025984,0.4786528859163277,0.5454545454545454,0.5340909090909091,0.5340909090909091,0.5340909090909091,0.5,0.45454545454545453,0.39204545454545453
 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
+Sailor2-8B-Chat,0.5405844155844156,0.5628246753246753,0.551480408610067,0.625,0.5852272727272727,0.4943181818181818,0.5568181818181818,0.5056818181818182,0.5568181818181818,0.4602272727272727
 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
+merged_llama3_8b_sg_inst_avg_diff,0.4829545454545454,0.4952922077922078,0.48904557518459746,0.5397727272727273,0.5340909090909091,0.4772727272727273,0.5056818181818182,0.4602272727272727,0.45454545454545453,0.4090909090909091
 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
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.6436688311688312,0.5938311688311688,0.6177464473895627,0.
 gemma2-9b-cpt-sea-lionv3-instruct,0.6055194805194805,0.6220779220779219,0.6136870270197391,0.6590909090909091,0.6590909090909091,0.5625,0.6193181818181818,0.5681818181818182,0.5852272727272727,0.5852272727272727
 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
-cross_openhermes_llama3_8b_12288_inst,0.48701298701298695,0.46964285714285725,0.4781702261263516,0.5511363636363636,0.5227272727272727,0.4715909090909091,0.4772727272727273,0.4943181818181818,0.5056818181818182,0.38636363636363635
 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

results/cross_lingual/zero_shot/cross_logiqa_no_prompt.csv

@@ -1,6 +1,9 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
-llama3-8b-cpt-sea-lionv2.1-instruct,0.4375,0.2728896103896104,0.3361231717991198,0.4318181818181818,0.4772727272727273,0.4943181818181818,0.4034090909090909,0.4318181818181818,0.42613636363636365,0.3977272727272727
-Meta-Llama-3-8B-Instruct,0.41558441558441567,0.24577922077922076,0.3088830658319437,0.45454545454545453,0.4772727272727273,0.42045454545454547,0.3522727272727273,0.3977272727272727,0.42613636363636365,0.3806818181818182
-gemma2-9b-cpt-sea-lionv3-instruct,0.48214285714285715,0.3753246753246754,0.4220803807589114,0.5454545454545454,0.5227272727272727,0.4943181818181818,0.4431818181818182,0.45454545454545453,0.4318181818181818,0.48295454545454547
-cross_openhermes_llama3_8b_12288_inst,0.3896103896103896,0.23279220779220777,0.2914456435114937,0.4659090909090909,0.3806818181818182,0.4147727272727273,0.30113636363636365,0.3693181818181818,0.42613636363636365,0.3693181818181818
-GPT4o_0513,0.575487012987013,0.4172077922077923,0.48372906728622567,0.6534090909090909,0.6079545454545454,0.6022727272727273,0.4659090909090909,0.5511363636363636,0.5965909090909091,0.5511363636363636
+Meta-Llama-3.1-8B-Instruct,0.512987012987013,0.4394480519480519,0.4733785048611023,0.5852272727272727,0.5852272727272727,0.5454545454545454,0.5,0.45454545454545453,0.5227272727272727,0.3977272727272727
+llama3-8b-cpt-sea-lionv2.1-instruct,0.45779220779220786,0.3751623376623376,0.412378792469608,0.5284090909090909,0.5170454545454546,0.5340909090909091,0.4602272727272727,0.4034090909090909,0.4431818181818182,0.3181818181818182
+Qwen2_5_7B_Instruct,0.6047077922077922,0.47938311688311697,0.5348014705675028,0.6931818181818182,0.7102272727272727,0.6420454545454546,0.5795454545454546,0.6306818181818182,0.5340909090909091,0.4431818181818182
+Sailor2-8B-Chat,0.5503246753246753,0.5363636363636365,0.5432544747850031,0.6136363636363636,0.625,0.5056818181818182,0.5625,0.5113636363636364,0.5511363636363636,0.48295454545454547
+merged_llama3_8b_sg_inst_avg_diff,0.5105519480519481,0.4558441558441559,0.48164954476113636,0.5909090909090909,0.5284090909090909,0.5454545454545454,0.5,0.4943181818181818,0.48863636363636365,0.42613636363636365
+SeaLLMs-v3-7B-Chat,0.5324675324675324,0.41266233766233773,0.46497164802104307,0.5681818181818182,0.5852272727272727,0.5738636363636364,0.5568181818181818,0.4943181818181818,0.5170454545454546,0.4318181818181818
+gemma-2-9b-it,0.6006493506493508,0.5753246753246755,0.587714328691409,0.6590909090909091,0.6363636363636364,0.5511363636363636,0.6022727272727273,0.5852272727272727,0.6022727272727273,0.5681818181818182
+gemma2-9b-cpt-sea-lionv3-instruct,0.5844155844155844,0.605844155844156,0.5949369778657175,0.6363636363636364,0.6420454545454546,0.5625,0.5681818181818182,0.5568181818181818,0.5511363636363636,0.5738636363636364

results/cross_lingual/zero_shot/cross_mmlu.csv

@@ -1,12 +1,14 @@
 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
+Meta-Llama-3.1-8B-Instruct,0.62,0.5765714285714285,0.5974976121754717,0.72,0.6133333333333333,0.6266666666666667,0.6066666666666667,0.5866666666666667,0.58,0.6066666666666667
 llama3-8b-cpt-sea-lionv2.1-instruct,0.6114285714285713,0.5478095238095239,0.5778733392299966,0.72,0.6,0.6066666666666667,0.62,0.6466666666666666,0.56,0.5266666666666666
 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
+Sailor2-8B-Chat,0.6542857142857142,0.6586666666666667,0.6564688814239598,0.7133333333333334,0.6733333333333333,0.6533333333333333,0.6066666666666667,0.62,0.6466666666666666,0.6666666666666666
 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
+merged_llama3_8b_sg_inst_avg_diff,0.5980952380952381,0.5817142857142859,0.5897910419722433,0.76,0.5866666666666667,0.6266666666666667,0.5466666666666666,0.5666666666666667,0.5533333333333333,0.5466666666666666
 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
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.7266666666666666,0.680952380952381,0.7030672078887086,0.7
 gemma2-9b-cpt-sea-lionv3-instruct,0.7180952380952382,0.7485714285714284,0.7330166975381478,0.78,0.7133333333333334,0.7133333333333334,0.6866666666666666,0.7266666666666667,0.7,0.7066666666666667
 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
-cross_openhermes_llama3_8b_12288_inst,0.5733333333333333,0.5337142857142858,0.5528148657449711,0.6666666666666666,0.6,0.5466666666666666,0.5333333333333333,0.5666666666666667,0.5933333333333334,0.5066666666666667
 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

results/cross_lingual/zero_shot/cross_mmlu_no_prompt.csv

@@ -1,6 +1,11 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
-llama3-8b-cpt-sea-lionv2.1-instruct,0.6638095238095237,0.5363809523809523,0.5933304614797237,0.78,0.62,0.6933333333333334,0.64,0.66,0.6466666666666666,0.6066666666666667
+Meta-Llama-3.1-8B-Instruct,0.6876190476190477,0.5615238095238096,0.6182070607559236,0.82,0.6333333333333333,0.72,0.6666666666666666,0.66,0.6466666666666666,0.6666666666666666
+llama3-8b-cpt-sea-lionv2.1-instruct,0.6676190476190476,0.5590476190476189,0.6085285418019147,0.7533333333333333,0.6666666666666666,0.68,0.6333333333333333,0.6933333333333334,0.64,0.6066666666666667
+Qwen2_5_7B_Instruct,0.7742857142857141,0.6222857142857142,0.6900140284752591,0.8466666666666667,0.84,0.8266666666666667,0.74,0.7533333333333333,0.7133333333333334,0.7
+Sailor2-8B-Chat,0.6923809523809524,0.6592380952380954,0.6754031781322388,0.7266666666666667,0.7066666666666667,0.7133333333333334,0.6733333333333333,0.6733333333333333,0.6466666666666666,0.7066666666666667
 Meta-Llama-3-8B-Instruct,0.6428571428571429,0.49542857142857133,0.5595955249078094,0.7666666666666667,0.6533333333333333,0.7,0.6466666666666666,0.5733333333333334,0.5733333333333334,0.5866666666666667
+merged_llama3_8b_sg_inst_avg_diff,0.6980952380952381,0.5891428571428572,0.6390081595918414,0.8466666666666667,0.6933333333333334,0.6933333333333334,0.6933333333333334,0.7133333333333334,0.6133333333333333,0.6333333333333333
+SeaLLMs-v3-7B-Chat,0.7342857142857142,0.5765714285714287,0.6459409639562039,0.8333333333333334,0.7266666666666667,0.7866666666666666,0.7133333333333334,0.74,0.6866666666666666,0.6533333333333333
+gemma-2-9b-it,0.781904761904762,0.747047619047619,0.7640788528690432,0.84,0.7933333333333333,0.7866666666666666,0.7466666666666667,0.78,0.7466666666666667,0.78
 gemma2-9b-cpt-sea-lionv3-instruct,0.7809523809523808,0.7506666666666667,0.7655100940510849,0.8466666666666667,0.7866666666666666,0.7733333333333333,0.78,0.7933333333333333,0.7333333333333333,0.7533333333333333
-cross_openhermes_llama3_8b_12288_inst,0.6066666666666667,0.4874285714285715,0.54055013922636,0.7266666666666667,0.6,0.6,0.5866666666666667,0.58,0.5733333333333334,0.58
 GPT4o_0513,0.8819047619047619,0.8609523809523807,0.8713026281050943,0.9266666666666666,0.8866666666666667,0.9066666666666666,0.7933333333333333,0.88,0.9066666666666666,0.8733333333333333

results/cross_lingual/zero_shot/cross_xquad.csv

@@ -1,11 +1,12 @@
 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,,,
+Meta-Llama-3.1-8B-Instruct,0.9380252100840336,0.9021008403361345,0.919712353438052,0.9453781512605042,0.926890756302521,0.9411764705882353,0.938655462184874,,,
 llama3-8b-cpt-sea-lionv2.1-instruct,0.9361344537815126,0.9067226890756303,0.9211938673738631,0.9403361344537815,0.9260504201680673,0.9420168067226891,0.9361344537815126,,,
 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,,,
 Meta-Llama-3-8B-Instruct,0.9210084033613445,0.880672268907563,0.9003888121913395,0.9411764705882353,0.9033613445378151,0.9260504201680673,0.9134453781512605,,,
+merged_llama3_8b_sg_inst_avg_diff,0.9369747899159664,0.8936974789915966,0.9148245940061492,0.9470588235294117,0.9218487394957983,0.9403361344537815,0.938655462184874,,,
 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,,,
@@ -16,6 +17,5 @@ Qwen2_5_14B_Instruct,0.9581932773109244,0.9474789915966386,0.9528060148705768,0.
 gemma2-9b-cpt-sea-lionv3-instruct,0.9573529411764706,0.9365546218487395,0.9468395810403457,0.9638655462184874,0.9428571428571428,0.9605042016806723,0.9621848739495799,,,
 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,,,
-cross_openhermes_llama3_8b_12288_inst,0.9273109243697479,0.8850840336134453,0.9057055579353634,0.9394957983193277,0.9252100840336135,0.9218487394957983,0.9226890756302522,,,
 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,,,

results/cross_lingual/zero_shot/cross_xquad_no_prompt.csv

@@ -1,6 +1,11 @@
 Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino
-llama3-8b-cpt-sea-lionv2.1-instruct,0.9191176470588235,0.8352941176470587,0.87520339228777,0.9394957983193277,0.8932773109243698,0.9285714285714286,0.915126050420168,,,
+Meta-Llama-3.1-8B-Instruct,0.9168067226890756,0.8292016806722688,0.870806433460842,0.9436974789915966,0.8949579831932774,0.9201680672268907,0.9084033613445378,,,
+llama3-8b-cpt-sea-lionv2.1-instruct,0.928781512605042,0.8592436974789917,0.892660412722869,0.9470588235294117,0.9084033613445378,0.9352941176470588,0.9243697478991597,,,
+Qwen2_5_7B_Instruct,0.9069327731092437,0.8264705882352941,0.8648342089942876,0.9210084033613445,0.8991596638655462,0.9092436974789916,0.8983193277310925,,,
+Sailor2-8B-Chat,0.9086134453781513,0.8378151260504201,0.8717792421413649,0.9252100840336135,0.8949579831932774,0.9117647058823529,0.9025210084033614,,,
 Meta-Llama-3-8B-Instruct,0.9060924369747899,0.8224789915966386,0.8622634639161603,0.9319327731092437,0.8932773109243698,0.9134453781512605,0.8857142857142857,,,
+merged_llama3_8b_sg_inst_avg_diff,0.9117647058823529,0.8266806722689075,0.8671405721911006,0.9302521008403362,0.8899159663865546,0.9210084033613445,0.9058823529411765,,,
+SeaLLMs-v3-7B-Chat,0.8943277310924369,0.7991596638655463,0.8440696412045011,0.9210084033613445,0.8773109243697479,0.9,0.8789915966386554,,,
+gemma-2-9b-it,0.8668067226890757,0.7012605042016806,0.7752949732453414,0.8773109243697479,0.8529411764705882,0.8714285714285714,0.865546218487395,,,
 gemma2-9b-cpt-sea-lionv3-instruct,0.9315126050420168,0.8716386554621849,0.9005815677746684,0.9453781512605042,0.9142857142857143,0.9369747899159664,0.9294117647058824,,,
-cross_openhermes_llama3_8b_12288_inst,0.9054621848739496,0.8298319327731092,0.8659989418997561,0.9285714285714286,0.892436974789916,0.9134453781512605,0.8873949579831932,,,
 GPT4o_0513,0.8941176470588236,0.8014705882352942,0.8452629967360276,0.9302521008403362,0.8857142857142857,0.9168067226890756,0.8436974789915966,,,

results/cultural_reasoning/zero_shot/cn_eval.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.8285714285714286
-Meta-Llama-3.1-8B-Instruct,0.4857142857142857
+Meta-Llama-3.1-8B-Instruct,0.45714285714285713
 llama3-8b-cpt-sea-lionv2.1-instruct,0.5047619047619047
 Qwen2_5_32B_Instruct,0.8476190476190476
 Qwen2_5_7B_Instruct,0.8
 Qwen2_5_1_5B_Instruct,0.5523809523809524
 Qwen2-72B-Instruct,0.8285714285714286
+Sailor2-8B-Chat,0.7142857142857143
 Meta-Llama-3-8B-Instruct,0.4666666666666667
+merged_llama3_8b_sg_inst_avg_diff,0.5142857142857142
 Meta-Llama-3.1-70B-Instruct,0.5428571428571428
 Qwen2_5_3B_Instruct,0.7142857142857143
 SeaLLMs-v3-7B-Chat,0.819047619047619
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.8285714285714286
 gemma2-9b-cpt-sea-lionv3-instruct,0.5904761904761905
 gemma-2-2b-it,0.3619047619047619
 llama3-8b-cpt-sea-lionv2-instruct,0.49523809523809526
-cross_openhermes_llama3_8b_12288_inst,0.5523809523809524
 Qwen2_5_0_5B_Instruct,0.3619047619047619
 GPT4o_0513,0.8095238095238095

results/cultural_reasoning/zero_shot/ph_eval.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.52
-Meta-Llama-3.1-8B-Instruct,0.6
+Meta-Llama-3.1-8B-Instruct,0.57
 llama3-8b-cpt-sea-lionv2.1-instruct,0.56
 Qwen2_5_32B_Instruct,0.7
 Qwen2_5_7B_Instruct,0.55
 Qwen2_5_1_5B_Instruct,0.37
 Qwen2-72B-Instruct,0.62
+Sailor2-8B-Chat,0.53
 Meta-Llama-3-8B-Instruct,0.58
+merged_llama3_8b_sg_inst_avg_diff,0.54
 Meta-Llama-3.1-70B-Instruct,0.68
 Qwen2_5_3B_Instruct,0.4
 SeaLLMs-v3-7B-Chat,0.47
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.6
 gemma2-9b-cpt-sea-lionv3-instruct,0.59
 gemma-2-2b-it,0.4
 llama3-8b-cpt-sea-lionv2-instruct,0.56
-cross_openhermes_llama3_8b_12288_inst,0.52
 Qwen2_5_0_5B_Instruct,0.27
 GPT4o_0513,0.77

results/cultural_reasoning/zero_shot/sg_eval.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.6796116504854369
-Meta-Llama-3.1-8B-Instruct,0.5728155339805825
+Meta-Llama-3.1-8B-Instruct,0.6407766990291263
 llama3-8b-cpt-sea-lionv2.1-instruct,0.6601941747572816
 Qwen2_5_32B_Instruct,0.7184466019417476
 Qwen2_5_7B_Instruct,0.6699029126213593
 Qwen2_5_1_5B_Instruct,0.5048543689320388
 Qwen2-72B-Instruct,0.7378640776699029
+Sailor2-8B-Chat,0.6019417475728155
 Meta-Llama-3-8B-Instruct,0.6504854368932039
+merged_llama3_8b_sg_inst_avg_diff,0.6019417475728155
 Meta-Llama-3.1-70B-Instruct,0.7184466019417476
 Qwen2_5_3B_Instruct,0.6310679611650486
 SeaLLMs-v3-7B-Chat,0.7184466019417476
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.7669902912621359
 gemma2-9b-cpt-sea-lionv3-instruct,0.6796116504854369
 gemma-2-2b-it,0.5533980582524272
 llama3-8b-cpt-sea-lionv2-instruct,0.6504854368932039
-cross_openhermes_llama3_8b_12288_inst,0.6310679611650486
 Qwen2_5_0_5B_Instruct,0.4077669902912621
 GPT4o_0513,0.8446601941747572

results/cultural_reasoning/zero_shot/sg_eval_v1_cleaned.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.6323529411764706
-Meta-Llama-3.1-8B-Instruct,0.5294117647058824
+Meta-Llama-3.1-8B-Instruct,0.5735294117647058
 llama3-8b-cpt-sea-lionv2.1-instruct,0.6617647058823529
 Qwen2_5_32B_Instruct,0.6470588235294118
 Qwen2_5_7B_Instruct,0.5882352941176471
 Qwen2_5_1_5B_Instruct,0.47058823529411764
 Qwen2-72B-Instruct,0.6764705882352942
+Sailor2-8B-Chat,0.5735294117647058
 Meta-Llama-3-8B-Instruct,0.5882352941176471
+merged_llama3_8b_sg_inst_avg_diff,0.5441176470588235
 Meta-Llama-3.1-70B-Instruct,0.6617647058823529
 Qwen2_5_3B_Instruct,0.5882352941176471
 SeaLLMs-v3-7B-Chat,0.5882352941176471
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.6911764705882353
 gemma2-9b-cpt-sea-lionv3-instruct,0.6029411764705882
 gemma-2-2b-it,0.5147058823529411
 llama3-8b-cpt-sea-lionv2-instruct,0.6617647058823529
-cross_openhermes_llama3_8b_12288_inst,0.6029411764705882
 Qwen2_5_0_5B_Instruct,0.36764705882352944
 GPT4o_0513,0.8088235294117647

results/cultural_reasoning/zero_shot/sg_eval_v2_mcq.csv

@@ -1,15 +1,17 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7872727272727272
-Meta-Llama-3.1-8B-Instruct,0.7854545454545454
+Meta-Llama-3.1-8B-Instruct,0.8127272727272727
 llama3-8b-cpt-sea-lionv2.1-instruct,0.7836363636363637
 Qwen2_5_32B_Instruct,0.8436363636363636
 Qwen2_5_7B_Instruct,0.78
 Qwen2_5_1_5B_Instruct,0.6636363636363637
 Qwen2-72B-Instruct,0.8581818181818182
+Sailor2-8B-Chat,0.730909090909091
 Meta-Llama-3-8B-Instruct,0.7909090909090909
+merged_llama3_8b_sg_inst_avg_diff,0.8109090909090909
 Meta-Llama-3.1-70B-Instruct,0.8763636363636363
 Qwen2_5_3B_Instruct,0.72
-SeaLLMs-v3-7B-Chat,0.7836363636363637
+SeaLLMs-v3-7B-Chat,0.7909090909090909
 Qwen2_5_72B_Instruct,0.8618181818181818
 gemma-2-9b-it,0.8036363636363636
 Meta-Llama-3-70B-Instruct,0.8381818181818181
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.8345454545454546
 gemma2-9b-cpt-sea-lionv3-instruct,0.8090909090909091
 gemma-2-2b-it,0.7163636363636363
 llama3-8b-cpt-sea-lionv2-instruct,0.7763636363636364
-cross_openhermes_llama3_8b_12288_inst,0.7890909090909091
 Qwen2_5_0_5B_Instruct,0.5727272727272728
 GPT4o_0513,0.8709090909090909

results/cultural_reasoning/zero_shot/sg_eval_v2_mcq_no_prompt.csv

@@ -1,6 +1,11 @@
 Model,Accuracy
-llama3-8b-cpt-sea-lionv2.1-instruct,0.8
+Meta-Llama-3.1-8B-Instruct,0.7418181818181818
+llama3-8b-cpt-sea-lionv2.1-instruct,0.7945454545454546
+Qwen2_5_7B_Instruct,0.7654545454545455
+Sailor2-8B-Chat,0.7145454545454546
 Meta-Llama-3-8B-Instruct,0.8054545454545454
+merged_llama3_8b_sg_inst_avg_diff,0.7854545454545454
+SeaLLMs-v3-7B-Chat,0.7581818181818182
+gemma-2-9b-it,0.7618181818181818
 gemma2-9b-cpt-sea-lionv3-instruct,0.7818181818181819
-cross_openhermes_llama3_8b_12288_inst,0.7945454545454546
 GPT4o_0513,0.9072727272727272

results/cultural_reasoning/zero_shot/sg_eval_v2_open.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,56.559999999999995
-Meta-Llama-3.1-8B-Instruct,49.2
+Meta-Llama-3.1-8B-Instruct,47.839999999999996
 llama3-8b-cpt-sea-lionv2.1-instruct,50.03999999999999
 Qwen2_5_32B_Instruct,53.2
 Qwen2_5_7B_Instruct,50.279999999999994
 Qwen2_5_1_5B_Instruct,44.480000000000004
 Qwen2-72B-Instruct,54.080000000000005
+Sailor2-8B-Chat,54.36
 Meta-Llama-3-8B-Instruct,51.120000000000005
+merged_llama3_8b_sg_inst_avg_diff,49.2
 Meta-Llama-3.1-70B-Instruct,51.31999999999999
 Qwen2_5_3B_Instruct,47.24
 SeaLLMs-v3-7B-Chat,55.0
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,53.2
 gemma2-9b-cpt-sea-lionv3-instruct,55.0
 gemma-2-2b-it,52.08
 llama3-8b-cpt-sea-lionv2-instruct,50.03999999999999
-cross_openhermes_llama3_8b_12288_inst,52.480000000000004
 Qwen2_5_0_5B_Instruct,35.28
 GPT4o_0513,57.28

results/cultural_reasoning/zero_shot/us_eval.csv

@@ -6,7 +6,9 @@ Qwen2_5_32B_Instruct,0.8411214953271028
 Qwen2_5_7B_Instruct,0.7663551401869159
 Qwen2_5_1_5B_Instruct,0.5981308411214953
 Qwen2-72B-Instruct,0.8785046728971962
+Sailor2-8B-Chat,0.7009345794392523
 Meta-Llama-3-8B-Instruct,0.7009345794392523
+merged_llama3_8b_sg_inst_avg_diff,0.7383177570093458
 Meta-Llama-3.1-70B-Instruct,0.8411214953271028
 Qwen2_5_3B_Instruct,0.6728971962616822
 SeaLLMs-v3-7B-Chat,0.6915887850467289
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.822429906542056
 gemma2-9b-cpt-sea-lionv3-instruct,0.8037383177570093
 gemma-2-2b-it,0.6915887850467289
 llama3-8b-cpt-sea-lionv2-instruct,0.7009345794392523
-cross_openhermes_llama3_8b_12288_inst,0.7663551401869159
 Qwen2_5_0_5B_Instruct,0.37383177570093457
 GPT4o_0513,0.8691588785046729

results/dialogue/zero_shot/dialogsum.csv

@@ -1,12 +1,14 @@
 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
+Meta-Llama-3.1-8B-Instruct,0.25246410428426797,0.3568915790041648,0.1259705585621535,0.27453017528648554
 llama3-8b-cpt-sea-lionv2.1-instruct,0.2538187048721643,0.3556160487203703,0.12835761178300684,0.27748245411311584
 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
+Sailor2-8B-Chat,0.19777087324327317,0.2970393044008424,0.07701994204737679,0.21925337328160027
 Meta-Llama-3-8B-Instruct,0.23978455271183616,0.33971099717559883,0.1203340311564728,0.2593086298034369
+merged_llama3_8b_sg_inst_avg_diff,0.25236243090492,0.3573462392196718,0.125506438977953,0.27423461451713527
 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
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.2343478938479703,0.3386251381162625,0.10742381514017992,0
 gemma2-9b-cpt-sea-lionv3-instruct,0.23790909190042164,0.34294544984076464,0.1078722585042388,0.26290956735626153
 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
-cross_openhermes_llama3_8b_12288_inst,0.27081377092899106,0.3746700335717668,0.1422316280821482,0.2955396511330582
 Qwen2_5_0_5B_Instruct,0.19408176276624156,0.28989753303423227,0.07842728643649079,0.21392046882800164
 GPT4o_0513,0.2375730297294346,0.3364674648846549,0.11718194476069822,0.25906967954295057

results/dialogue/zero_shot/dream.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.9353258206761391
-Meta-Llama-3.1-8B-Instruct,0.9039686428221461
+Meta-Llama-3.1-8B-Instruct,0.9054385105340519
 llama3-8b-cpt-sea-lionv2.1-instruct,0.8838804507594317
 Qwen2_5_32B_Instruct,0.9559039686428221
 Qwen2_5_7B_Instruct,0.9348358647721705
 Qwen2_5_1_5B_Instruct,0.8314551690347869
 Qwen2-72B-Instruct,0.9612934835864773
+Sailor2-8B-Chat,0.9054385105340519
 Meta-Llama-3-8B-Instruct,0.8946594806467418
+merged_llama3_8b_sg_inst_avg_diff,0.9103380695737384
 Meta-Llama-3.1-70B-Instruct,0.9559039686428221
 Qwen2_5_3B_Instruct,0.9029887310142087
 SeaLLMs-v3-7B-Chat,0.9265066144047036
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.9461048505634493
 gemma2-9b-cpt-sea-lionv3-instruct,0.9407153356197943
 gemma-2-2b-it,0.8510534051935326
 llama3-8b-cpt-sea-lionv2-instruct,0.8858402743753062
-cross_openhermes_llama3_8b_12288_inst,0.8829005389514943
 Qwen2_5_0_5B_Instruct,0.6526212640862322
 GPT4o_0513,0.9583537481626654

results/dialogue/zero_shot/samsum.csv

@@ -1,12 +1,14 @@
 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
+Meta-Llama-3.1-8B-Instruct,0.2820716862174726,0.39415911433028605,0.148351765041582,0.30370417928054966
 llama3-8b-cpt-sea-lionv2.1-instruct,0.3049906423685726,0.42002411403511675,0.16877419641049218,0.32617361666010874
 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
+Sailor2-8B-Chat,0.23525560304744508,0.34567892481583223,0.10170204161284628,0.2583858427136568
 Meta-Llama-3-8B-Instruct,0.2846315092346869,0.39397110152251813,0.154320846916639,0.30560257926490364
+merged_llama3_8b_sg_inst_avg_diff,0.2827552959388026,0.3953429193664384,0.14797005050571224,0.30495291794425716
 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
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.2713801253928723,0.3836253496005304,0.13683087953788298,0
 gemma2-9b-cpt-sea-lionv3-instruct,0.29509358497900623,0.4129497614150914,0.1502573048316353,0.32207368869029196
 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
-cross_openhermes_llama3_8b_12288_inst,0.30043920936284546,0.41309659421156786,0.16636483587009585,0.3218561980068726
 Qwen2_5_0_5B_Instruct,0.20766179544894214,0.3105872033328297,0.08726222085933319,0.22513596215466355
 GPT4o_0513,0.27736679291505306,0.386750207633093,0.14889081847621596,0.2964593526358502

results/emotion/zero_shot/ind_emotion.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.6545454545454545
-Meta-Llama-3.1-8B-Instruct,0.6545454545454545
+Meta-Llama-3.1-8B-Instruct,0.6772727272727272
 llama3-8b-cpt-sea-lionv2.1-instruct,0.6681818181818182
 Qwen2_5_32B_Instruct,0.6909090909090909
 Qwen2_5_7B_Instruct,0.6636363636363637
 Qwen2_5_1_5B_Instruct,0.5795454545454546
 Qwen2-72B-Instruct,0.675
+Sailor2-8B-Chat,0.7363636363636363
 Meta-Llama-3-8B-Instruct,0.6522727272727272
+merged_llama3_8b_sg_inst_avg_diff,0.7
 Meta-Llama-3.1-70B-Instruct,0.7159090909090909
 Qwen2_5_3B_Instruct,0.5522727272727272
 SeaLLMs-v3-7B-Chat,0.6454545454545455
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.6954545454545454
 gemma2-9b-cpt-sea-lionv3-instruct,0.7340909090909091
 gemma-2-2b-it,0.6636363636363637
 llama3-8b-cpt-sea-lionv2-instruct,0.6613636363636364
-cross_openhermes_llama3_8b_12288_inst,0.7045454545454546
 Qwen2_5_0_5B_Instruct,0.37727272727272726
 GPT4o_0513,0.7068181818181818

results/emotion/zero_shot/sst2.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.9346330275229358
-Meta-Llama-3.1-8B-Instruct,0.8646788990825688
+Meta-Llama-3.1-8B-Instruct,0.8956422018348624
 llama3-8b-cpt-sea-lionv2.1-instruct,0.9174311926605505
 Qwen2_5_32B_Instruct,0.9472477064220184
 Qwen2_5_7B_Instruct,0.9254587155963303
 Qwen2_5_1_5B_Instruct,0.9231651376146789
 Qwen2-72B-Instruct,0.9346330275229358
+Sailor2-8B-Chat,0.9461009174311926
 Meta-Llama-3-8B-Instruct,0.8784403669724771
+merged_llama3_8b_sg_inst_avg_diff,0.8841743119266054
 Meta-Llama-3.1-70B-Instruct,0.9529816513761468
 Qwen2_5_3B_Instruct,0.8245412844036697
 SeaLLMs-v3-7B-Chat,0.9403669724770642
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.9311926605504587
 gemma2-9b-cpt-sea-lionv3-instruct,0.9311926605504587
 gemma-2-2b-it,0.9243119266055045
 llama3-8b-cpt-sea-lionv2-instruct,0.9128440366972477
-cross_openhermes_llama3_8b_12288_inst,0.9288990825688074
 Qwen2_5_0_5B_Instruct,0.7889908256880734
 GPT4o_0513,0.9415137614678899

results/flores_translation/zero_shot/ind2eng.csv

@@ -1,12 +1,14 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.29408553325533265
-Meta-Llama-3.1-8B-Instruct,0.3765752579792989
+Meta-Llama-3.1-8B-Instruct,0.37357029870421904
 llama3-8b-cpt-sea-lionv2.1-instruct,0.38890283520513874
 Qwen2_5_32B_Instruct,0.3923422946746861
 Qwen2_5_7B_Instruct,0.36472669481333536
 Qwen2_5_1_5B_Instruct,0.2624938515155373
 Qwen2-72B-Instruct,0.4043588265556185
+Sailor2-8B-Chat,0.2487972955646591
 Meta-Llama-3-8B-Instruct,0.33079891679041123
+merged_llama3_8b_sg_inst_avg_diff,0.38376586000725804
 Meta-Llama-3.1-70B-Instruct,0.43366494500251235
 Qwen2_5_3B_Instruct,0.3316936422167389
 SeaLLMs-v3-7B-Chat,0.3594829412574955
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.3901044620348051
 gemma2-9b-cpt-sea-lionv3-instruct,0.3922444585880475
 gemma-2-2b-it,0.3482500758113138
 llama3-8b-cpt-sea-lionv2-instruct,0.3916108972514423
-cross_openhermes_llama3_8b_12288_inst,0.3900675406718024
 Qwen2_5_0_5B_Instruct,0.15776662800152338
 GPT4o_0513,0.42589589086974855

results/flores_translation/zero_shot/vie2eng.csv

@@ -1,12 +1,14 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.24106736560355876
-Meta-Llama-3.1-8B-Instruct,0.31019605539004524
+Meta-Llama-3.1-8B-Instruct,0.30308791998756773
 llama3-8b-cpt-sea-lionv2.1-instruct,0.32831099820283755
 Qwen2_5_32B_Instruct,0.33791529833420336
 Qwen2_5_7B_Instruct,0.3027564749728372
 Qwen2_5_1_5B_Instruct,0.21935649300365245
 Qwen2-72B-Instruct,0.33005323227052946
+Sailor2-8B-Chat,0.1825857920682635
 Meta-Llama-3-8B-Instruct,0.2647448190950291
+merged_llama3_8b_sg_inst_avg_diff,0.30900856944791294
 Meta-Llama-3.1-70B-Instruct,0.37244508311079816
 Qwen2_5_3B_Instruct,0.27312609009801636
 SeaLLMs-v3-7B-Chat,0.30981028289420137
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.32198218156960645
 gemma2-9b-cpt-sea-lionv3-instruct,0.3176282835521885
 gemma-2-2b-it,0.27518909199172303
 llama3-8b-cpt-sea-lionv2-instruct,0.327781936019637
-cross_openhermes_llama3_8b_12288_inst,0.29952664743728336
 Qwen2_5_0_5B_Instruct,0.14677375445859656
 GPT4o_0513,0.36219303373759176

results/flores_translation/zero_shot/zho2eng.csv

@@ -1,12 +1,14 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.2113761361724575
-Meta-Llama-3.1-8B-Instruct,0.23889886925287113
+Meta-Llama-3.1-8B-Instruct,0.2429198421592902
 llama3-8b-cpt-sea-lionv2.1-instruct,0.2378480031503388
 Qwen2_5_32B_Instruct,0.26924811164378015
 Qwen2_5_7B_Instruct,0.2437311220019033
 Qwen2_5_1_5B_Instruct,0.18420680441018222
 Qwen2-72B-Instruct,0.23893268538329387
+Sailor2-8B-Chat,0.16539980828035464
 Meta-Llama-3-8B-Instruct,0.199495011482748
+merged_llama3_8b_sg_inst_avg_diff,0.24133164017585856
 Meta-Llama-3.1-70B-Instruct,0.2832594176173152
 Qwen2_5_3B_Instruct,0.2245195134637718
 SeaLLMs-v3-7B-Chat,0.2516593644617717
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.2627781200417998
 gemma2-9b-cpt-sea-lionv3-instruct,0.25110750921976727
 gemma-2-2b-it,0.21164036008441425
 llama3-8b-cpt-sea-lionv2-instruct,0.2381535278220489
-cross_openhermes_llama3_8b_12288_inst,0.2437964546132799
 Qwen2_5_0_5B_Instruct,0.13846648470535672
 GPT4o_0513,0.27722306559544163

results/flores_translation/zero_shot/zsm2eng.csv

@@ -1,12 +1,14 @@
 Model,BLEU
 Qwen2-7B-Instruct,0.28031997065822994
-Meta-Llama-3.1-8B-Instruct,0.3700921225177551
+Meta-Llama-3.1-8B-Instruct,0.36579667849635744
 llama3-8b-cpt-sea-lionv2.1-instruct,0.39042133634273773
 Qwen2_5_32B_Instruct,0.40310877536446654
 Qwen2_5_7B_Instruct,0.3466422765302921
 Qwen2_5_1_5B_Instruct,0.22890805100949677
 Qwen2-72B-Instruct,0.40796892621611885
+Sailor2-8B-Chat,0.269986448536842
 Meta-Llama-3-8B-Instruct,0.31625368345049
+merged_llama3_8b_sg_inst_avg_diff,0.3729790018011108
 Meta-Llama-3.1-70B-Instruct,0.4462132282683508
 Qwen2_5_3B_Instruct,0.31056841204320457
 SeaLLMs-v3-7B-Chat,0.3484133510670942
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.3841042767934729
 gemma2-9b-cpt-sea-lionv3-instruct,0.4059485540822735
 gemma-2-2b-it,0.33737270487369614
 llama3-8b-cpt-sea-lionv2-instruct,0.38799258214381604
-cross_openhermes_llama3_8b_12288_inst,0.39589080400186966
 Qwen2_5_0_5B_Instruct,0.1194369315142997
 GPT4o_0513,0.451496635720668

results/fundamental_nlp_tasks/zero_shot/c3.csv

@@ -1,12 +1,13 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.9244577412116679
-Meta-Llama-3.1-8B-Instruct,0.8672400897531788
+Meta-Llama-3.1-8B-Instruct,0.8814510097232611
 llama3-8b-cpt-sea-lionv2.1-instruct,0.8676140613313388
 Qwen2_5_32B_Instruct,0.9603590127150337
 Qwen2_5_7B_Instruct,0.9121166791323859
 Qwen2_5_1_5B_Instruct,0.793941660433807
 Qwen2-72B-Instruct,0.9611069558713538
 Meta-Llama-3-8B-Instruct,0.8515332834704562
+merged_llama3_8b_sg_inst_avg_diff,0.8706058339566193
 Meta-Llama-3.1-70B-Instruct,0.9603590127150337
 Qwen2_5_3B_Instruct,0.8668661181750187
 SeaLLMs-v3-7B-Chat,0.9143605086013463
@@ -18,6 +19,5 @@ Meta-Llama-3.1-70B,0.7786088257292446
 gemma2-9b-cpt-sea-lionv3-instruct,0.9255796559461481
 gemma-2-2b-it,0.7700074794315632
 llama3-8b-cpt-sea-lionv2-instruct,0.8672400897531788
-cross_openhermes_llama3_8b_12288_inst,0.8485415108451758
 Qwen2_5_0_5B_Instruct,0.612939416604338
 GPT4o_0513,0.9648466716529543

results/fundamental_nlp_tasks/zero_shot/cola.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7871524448705657
-Meta-Llama-3.1-8B-Instruct,0.6673058485139022
+Meta-Llama-3.1-8B-Instruct,0.6519654841802492
 llama3-8b-cpt-sea-lionv2.1-instruct,0.613614573346117
 Qwen2_5_32B_Instruct,0.8427612655800575
 Qwen2_5_7B_Instruct,0.7909875359539789
 Qwen2_5_1_5B_Instruct,0.7497603068072867
 Qwen2-72B-Instruct,0.8341323106423778
+Sailor2-8B-Chat,0.7900287631831256
 Meta-Llama-3-8B-Instruct,0.6548418024928092
+merged_llama3_8b_sg_inst_avg_diff,0.6174496644295302
 Meta-Llama-3.1-70B-Instruct,0.850431447746884
 Qwen2_5_3B_Instruct,0.6644295302013423
 SeaLLMs-v3-7B-Chat,0.785234899328859
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.8063279002876318
 gemma2-9b-cpt-sea-lionv3-instruct,0.825503355704698
 gemma-2-2b-it,0.6749760306807286
 llama3-8b-cpt-sea-lionv2-instruct,0.6078619367209971
-cross_openhermes_llama3_8b_12288_inst,0.8207094918504314
 Qwen2_5_0_5B_Instruct,0.6116970278044104
 GPT4o_0513,0.8398849472674976

results/fundamental_nlp_tasks/zero_shot/mnli.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7295
-Meta-Llama-3.1-8B-Instruct,0.4825
+Meta-Llama-3.1-8B-Instruct,0.5295
 llama3-8b-cpt-sea-lionv2.1-instruct,0.5775
 Qwen2_5_32B_Instruct,0.8715
 Qwen2_5_7B_Instruct,0.8105
 Qwen2_5_1_5B_Instruct,0.6045
 Qwen2-72B-Instruct,0.7925
+Sailor2-8B-Chat,0.664
 Meta-Llama-3-8B-Instruct,0.546
+merged_llama3_8b_sg_inst_avg_diff,0.5375
 Meta-Llama-3.1-70B-Instruct,0.7015
 Qwen2_5_3B_Instruct,0.7465
 SeaLLMs-v3-7B-Chat,0.653
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.818
 gemma2-9b-cpt-sea-lionv3-instruct,0.7445
 gemma-2-2b-it,0.6185
 llama3-8b-cpt-sea-lionv2-instruct,0.5765
-cross_openhermes_llama3_8b_12288_inst,0.6485
 Qwen2_5_0_5B_Instruct,0.5095
 GPT4o_0513,0.8335

results/fundamental_nlp_tasks/zero_shot/mrpc.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7867647058823529
-Meta-Llama-3.1-8B-Instruct,0.6740196078431373
+Meta-Llama-3.1-8B-Instruct,0.6666666666666666
 llama3-8b-cpt-sea-lionv2.1-instruct,0.5808823529411765
 Qwen2_5_32B_Instruct,0.7745098039215687
 Qwen2_5_7B_Instruct,0.7058823529411765
 Qwen2_5_1_5B_Instruct,0.6838235294117647
 Qwen2-72B-Instruct,0.8063725490196079
+Sailor2-8B-Chat,0.7769607843137255
 Meta-Llama-3-8B-Instruct,0.678921568627451
+merged_llama3_8b_sg_inst_avg_diff,0.6274509803921569
 Meta-Llama-3.1-70B-Instruct,0.7696078431372549
 Qwen2_5_3B_Instruct,0.5661764705882353
 SeaLLMs-v3-7B-Chat,0.7475490196078431
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.7794117647058824
 gemma2-9b-cpt-sea-lionv3-instruct,0.7794117647058824
 gemma-2-2b-it,0.7083333333333334
 llama3-8b-cpt-sea-lionv2-instruct,0.5833333333333334
-cross_openhermes_llama3_8b_12288_inst,0.6985294117647058
 Qwen2_5_0_5B_Instruct,0.5759803921568627
 GPT4o_0513,0.7377450980392157

results/fundamental_nlp_tasks/zero_shot/ocnli.csv

@@ -1,11 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.6542372881355932
-Meta-Llama-3.1-8B-Instruct,0.40983050847457625
+Meta-Llama-3.1-8B-Instruct,0.4359322033898305
+llama3-8b-cpt-sea-lionv2.1-instruct,0.4559322033898305
 Qwen2_5_32B_Instruct,0.7742372881355932
 Qwen2_5_7B_Instruct,0.6732203389830509
 Qwen2_5_1_5B_Instruct,0.5135593220338983
 Qwen2-72B-Instruct,0.7820338983050847
+Sailor2-8B-Chat,0.5569491525423729
 Meta-Llama-3-8B-Instruct,0.44033898305084745
+merged_llama3_8b_sg_inst_avg_diff,0.4633898305084746
 Meta-Llama-3.1-70B-Instruct,0.6423728813559322
 Qwen2_5_3B_Instruct,0.6145762711864406
 SeaLLMs-v3-7B-Chat,0.5698305084745763
@@ -16,6 +19,5 @@ Qwen2_5_14B_Instruct,0.7538983050847458
 gemma2-9b-cpt-sea-lionv3-instruct,0.6488135593220339
 gemma-2-2b-it,0.43322033898305085
 llama3-8b-cpt-sea-lionv2-instruct,0.45559322033898303
-cross_openhermes_llama3_8b_12288_inst,0.5925423728813559
 Qwen2_5_0_5B_Instruct,0.3847457627118644
 GPT4o_0513,0.7308474576271187

results/fundamental_nlp_tasks/zero_shot/qnli.csv

@@ -1,11 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.8154859967051071
-Meta-Llama-3.1-8B-Instruct,0.5777045579352005
+Meta-Llama-3.1-8B-Instruct,0.6128500823723229
+llama3-8b-cpt-sea-lionv2.1-instruct,0.610287387882116
 Qwen2_5_32B_Instruct,0.9062786015010068
 Qwen2_5_7B_Instruct,0.8652754896576972
 Qwen2_5_1_5B_Instruct,0.6148636280431997
 Qwen2-72B-Instruct,0.8887058392824455
+Sailor2-8B-Chat,0.6822258832143511
 Meta-Llama-3-8B-Instruct,0.6025993044114956
+merged_llama3_8b_sg_inst_avg_diff,0.6522057477576423
 Meta-Llama-3.1-70B-Instruct,0.9026176093721399
 Qwen2_5_3B_Instruct,0.7645982061138569
 SeaLLMs-v3-7B-Chat,0.7159070107999268
@@ -16,6 +19,5 @@ Qwen2_5_14B_Instruct,0.9079260479589969
 gemma2-9b-cpt-sea-lionv3-instruct,0.9055464030752334
 gemma-2-2b-it,0.7792421746293245
 llama3-8b-cpt-sea-lionv2-instruct,0.6101043382756727
-cross_openhermes_llama3_8b_12288_inst,0.8282994691561413
 Qwen2_5_0_5B_Instruct,0.5464030752333883
 GPT4o_0513,0.9304411495515285

results/fundamental_nlp_tasks/zero_shot/qqp.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.781
-Meta-Llama-3.1-8B-Instruct,0.5645
+Meta-Llama-3.1-8B-Instruct,0.6175
 llama3-8b-cpt-sea-lionv2.1-instruct,0.625
 Qwen2_5_32B_Instruct,0.8315
 Qwen2_5_7B_Instruct,0.76
 Qwen2_5_1_5B_Instruct,0.731
 Qwen2-72B-Instruct,0.8065
+Sailor2-8B-Chat,0.8205
 Meta-Llama-3-8B-Instruct,0.563
+merged_llama3_8b_sg_inst_avg_diff,0.597
 Meta-Llama-3.1-70B-Instruct,0.815
 Qwen2_5_3B_Instruct,0.7415
 SeaLLMs-v3-7B-Chat,0.7625
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.8255
 gemma2-9b-cpt-sea-lionv3-instruct,0.803
 gemma-2-2b-it,0.761
 llama3-8b-cpt-sea-lionv2-instruct,0.6225
-cross_openhermes_llama3_8b_12288_inst,0.792
 Qwen2_5_0_5B_Instruct,0.619
 GPT4o_0513,0.8085

results/fundamental_nlp_tasks/zero_shot/rte.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.8231046931407943
-Meta-Llama-3.1-8B-Instruct,0.6750902527075813
+Meta-Llama-3.1-8B-Instruct,0.6389891696750902
 llama3-8b-cpt-sea-lionv2.1-instruct,0.6859205776173285
 Qwen2_5_32B_Instruct,0.9097472924187726
 Qwen2_5_7B_Instruct,0.8592057761732852
 Qwen2_5_1_5B_Instruct,0.703971119133574
 Qwen2-72B-Instruct,0.8447653429602888
+Sailor2-8B-Chat,0.8122743682310469
 Meta-Llama-3-8B-Instruct,0.6173285198555957
+merged_llama3_8b_sg_inst_avg_diff,0.6606498194945848
 Meta-Llama-3.1-70B-Instruct,0.8483754512635379
 Qwen2_5_3B_Instruct,0.779783393501805
 SeaLLMs-v3-7B-Chat,0.7870036101083032
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.8664259927797834
 gemma2-9b-cpt-sea-lionv3-instruct,0.8483754512635379
 gemma-2-2b-it,0.7292418772563177
 llama3-8b-cpt-sea-lionv2-instruct,0.6859205776173285
-cross_openhermes_llama3_8b_12288_inst,0.8050541516245487
 Qwen2_5_0_5B_Instruct,0.5992779783393501
 GPT4o_0513,0.8700361010830325

results/fundamental_nlp_tasks/zero_shot/wnli.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7183098591549296
-Meta-Llama-3.1-8B-Instruct,0.49295774647887325
+Meta-Llama-3.1-8B-Instruct,0.6197183098591549
 llama3-8b-cpt-sea-lionv2.1-instruct,0.5915492957746479
 Qwen2_5_32B_Instruct,0.8732394366197183
 Qwen2_5_7B_Instruct,0.7605633802816901
 Qwen2_5_1_5B_Instruct,0.4647887323943662
 Qwen2-72B-Instruct,0.8873239436619719
+Sailor2-8B-Chat,0.5492957746478874
 Meta-Llama-3-8B-Instruct,0.4788732394366197
+merged_llama3_8b_sg_inst_avg_diff,0.5492957746478874
 Meta-Llama-3.1-70B-Instruct,0.8450704225352113
 Qwen2_5_3B_Instruct,0.647887323943662
 SeaLLMs-v3-7B-Chat,0.5915492957746479
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.8309859154929577
 gemma2-9b-cpt-sea-lionv3-instruct,0.7605633802816901
 gemma-2-2b-it,0.43661971830985913
 llama3-8b-cpt-sea-lionv2-instruct,0.5774647887323944
-cross_openhermes_llama3_8b_12288_inst,0.5211267605633803
 Qwen2_5_0_5B_Instruct,0.43661971830985913
 GPT4o_0513,0.9295774647887324

results/general_reasoning/zero_shot/c_eval.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7615193026151931
-Meta-Llama-3.1-8B-Instruct,0.5149439601494396
+Meta-Llama-3.1-8B-Instruct,0.5180572851805728
 llama3-8b-cpt-sea-lionv2.1-instruct,0.50186799501868
 Qwen2_5_32B_Instruct,0.8262764632627646
 Qwen2_5_7B_Instruct,0.7459526774595268
 Qwen2_5_1_5B_Instruct,0.5971357409713575
 Qwen2-72B-Instruct,0.8312577833125778
+Sailor2-8B-Chat,0.5946450809464509
 Meta-Llama-3-8B-Instruct,0.4775840597758406
+merged_llama3_8b_sg_inst_avg_diff,0.5205479452054794
 Meta-Llama-3.1-70B-Instruct,0.6612702366127023
 Qwen2_5_3B_Instruct,0.6537982565379825
 SeaLLMs-v3-7B-Chat,0.7658779576587795
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.7839352428393525
 gemma2-9b-cpt-sea-lionv3-instruct,0.5722291407222914
 gemma-2-2b-it,0.4352428393524284
 llama3-8b-cpt-sea-lionv2-instruct,0.49813200498132004
-cross_openhermes_llama3_8b_12288_inst,0.4863013698630137
 Qwen2_5_0_5B_Instruct,0.41718555417185554
 GPT4o_0513,0.7073474470734745

results/general_reasoning/zero_shot/cmmlu.csv

@@ -1,11 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7727508202383008
-Meta-Llama-3.1-8B-Instruct,0.5246934898981178
+Meta-Llama-3.1-8B-Instruct,0.5183042652391642
+llama3-8b-cpt-sea-lionv2.1-instruct,0.49222932136073216
 Qwen2_5_32B_Instruct,0.8273182524607149
 Qwen2_5_7B_Instruct,0.7486617164565705
 Qwen2_5_1_5B_Instruct,0.5975651873596961
 Qwen2-72B-Instruct,0.8293904334311863
+Sailor2-8B-Chat,0.6416853738559835
 Meta-Llama-3-8B-Instruct,0.4839405974788465
+merged_llama3_8b_sg_inst_avg_diff,0.5171818338801588
 Meta-Llama-3.1-70B-Instruct,0.6814885166637886
 Qwen2_5_3B_Instruct,0.6621481609393887
 SeaLLMs-v3-7B-Chat,0.7684337765498187
@@ -16,6 +19,5 @@ Qwen2_5_14B_Instruct,0.7807805214988776
 gemma2-9b-cpt-sea-lionv3-instruct,0.5796062856156105
 gemma-2-2b-it,0.4412882058366431
 llama3-8b-cpt-sea-lionv2-instruct,0.48929373165256435
-cross_openhermes_llama3_8b_12288_inst,0.48877568640994645
 Qwen2_5_0_5B_Instruct,0.42056639613192887
 GPT4o_0513,0.7414954239336902

results/general_reasoning/zero_shot/indommlu.csv

@@ -1,12 +1,13 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.5385539755657921
-Meta-Llama-3.1-8B-Instruct,0.5252687095266707
+Meta-Llama-3.1-8B-Instruct,0.5605180586153948
 llama3-8b-cpt-sea-lionv2.1-instruct,0.5269377127979171
 Qwen2_5_32B_Instruct,0.6314840777087923
 Qwen2_5_7B_Instruct,0.5600507376994459
 Qwen2_5_1_5B_Instruct,0.4295346818879765
 Qwen2-72B-Instruct,0.6385606515788771
 Meta-Llama-3-8B-Instruct,0.5264703918819681
+merged_llama3_8b_sg_inst_avg_diff,0.5724013619066693
 Meta-Llama-3.1-70B-Instruct,0.6740770411910008
 Qwen2_5_3B_Instruct,0.49656185326123237
 SeaLLMs-v3-7B-Chat,0.5267374324053675
@@ -17,6 +18,5 @@ Qwen2_5_14B_Instruct,0.6009746979104079
 gemma2-9b-cpt-sea-lionv3-instruct,0.6196007744175178
 gemma-2-2b-it,0.48220842512851325
 llama3-8b-cpt-sea-lionv2-instruct,0.5252687095266707
-cross_openhermes_llama3_8b_12288_inst,0.5533747246144602
 Qwen2_5_0_5B_Instruct,0.3279925228653448
 GPT4o_0513,0.7584618465852193

results/general_reasoning/zero_shot/indommlu_no_prompt.csv

@@ -1,6 +1,11 @@
 Model,Accuracy
-llama3-8b-cpt-sea-lionv2.1-instruct,0.5561786501101542
+Meta-Llama-3.1-8B-Instruct,0.5483009546698712
+llama3-8b-cpt-sea-lionv2.1-instruct,0.559516656652647
+Qwen2_5_7B_Instruct,0.581814540356499
+Sailor2-8B-Chat,0.6342212430736365
 Meta-Llama-3-8B-Instruct,0.5207957807597303
+merged_llama3_8b_sg_inst_avg_diff,0.575806128580012
+SeaLLMs-v3-7B-Chat,0.5406235396221376
+gemma-2-9b-it,0.6210027371653648
 gemma2-9b-cpt-sea-lionv3-instruct,0.6258762267174044
-cross_openhermes_llama3_8b_12288_inst,0.5279391147606649
 GPT4o_0513,0.7599305694639161

results/general_reasoning/zero_shot/mmlu.csv

@@ -1,11 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.672506256703611
-Meta-Llama-3.1-8B-Instruct,0.6037182695745441
+Meta-Llama-3.1-8B-Instruct,0.6387558097962103
+llama3-8b-cpt-sea-lionv2.1-instruct,0.6117268501966393
 Qwen2_5_32B_Instruct,0.7996424740793707
 Qwen2_5_7B_Instruct,0.6935287808366106
 Qwen2_5_1_5B_Instruct,0.5646764390418305
 Qwen2-72B-Instruct,0.7922774401144083
+Sailor2-8B-Chat,0.6202359671076153
 Meta-Llama-3-8B-Instruct,0.6005720414730068
+merged_llama3_8b_sg_inst_avg_diff,0.631748301751877
 Meta-Llama-3.1-70B-Instruct,0.8058634250983197
 Qwen2_5_3B_Instruct,0.6118698605648909
 SeaLLMs-v3-7B-Chat,0.6670003575259207
@@ -16,6 +19,5 @@ Qwen2_5_14B_Instruct,0.7542366821594566
 gemma2-9b-cpt-sea-lionv3-instruct,0.7079013228459063
 gemma-2-2b-it,0.5706828745084018
 llama3-8b-cpt-sea-lionv2-instruct,0.6130854486950303
-cross_openhermes_llama3_8b_12288_inst,0.5870575616732213
 Qwen2_5_0_5B_Instruct,0.461136932427601
 GPT4o_0513,0.8308187343582409

results/general_reasoning/zero_shot/mmlu_no_prompt.csv

@@ -1,5 +1,10 @@
 Model,Accuracy
-llama3-8b-cpt-sea-lionv2.1-instruct,0.6551304969610297
+Meta-Llama-3.1-8B-Instruct,0.7056131569538792
+llama3-8b-cpt-sea-lionv2.1-instruct,0.6454057919199142
+Qwen2_5_7B_Instruct,0.73936360386128
 Meta-Llama-3-8B-Instruct,0.6618519842688595
-cross_openhermes_llama3_8b_12288_inst,0.6010010725777619
+merged_llama3_8b_sg_inst_avg_diff,0.6988916696460493
+SeaLLMs-v3-7B-Chat,0.6913836253128351
+gemma-2-9b-it,0.740293171254916
+gemma2-9b-cpt-sea-lionv3-instruct,0.7372899535216303
 GPT4o_0513,0.871576689309975

results/general_reasoning/zero_shot/zbench.csv

@@ -1,12 +1,14 @@
 Model,Accuracy
 Qwen2-7B-Instruct,0.7272727272727273
-Meta-Llama-3.1-8B-Instruct,0.42424242424242425
+Meta-Llama-3.1-8B-Instruct,0.3939393939393939
 llama3-8b-cpt-sea-lionv2.1-instruct,0.2727272727272727
 Qwen2_5_32B_Instruct,0.6060606060606061
 Qwen2_5_7B_Instruct,0.6666666666666666
 Qwen2_5_1_5B_Instruct,0.42424242424242425
 Qwen2-72B-Instruct,0.5757575757575758
+Sailor2-8B-Chat,0.5151515151515151
 Meta-Llama-3-8B-Instruct,0.3333333333333333
+merged_llama3_8b_sg_inst_avg_diff,0.42424242424242425
 Meta-Llama-3.1-70B-Instruct,0.48484848484848486
 Qwen2_5_3B_Instruct,0.5757575757575758
 SeaLLMs-v3-7B-Chat,0.5454545454545454
@@ -17,6 +19,5 @@ Qwen2_5_14B_Instruct,0.6666666666666666
 gemma2-9b-cpt-sea-lionv3-instruct,0.42424242424242425
 gemma-2-2b-it,0.24242424242424243
 llama3-8b-cpt-sea-lionv2-instruct,0.30303030303030304
-cross_openhermes_llama3_8b_12288_inst,0.42424242424242425
 Qwen2_5_0_5B_Instruct,0.36363636363636365
 GPT4o_0513,0.696969696969697