Spaces:
Running
Running
Model,Accuracy,Cross-Lingual Consistency,AC3,English,Chinese,Spanish,Vietnamese,Indonesian,Malay,Filipino | |
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-3.1-70B-Instruct,0.6566558441558442,0.598051948051948,0.6259852839118454,0.7443181818181818,0.7215909090909091,0.6647727272727273,0.6534090909090909,0.6193181818181818,0.625,0.5681818181818182 | |
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 | |
sg_llama3_70b_inst,0.6217532467532468,0.5629870129870129,0.590912649920049,0.7272727272727273,0.6590909090909091,0.6477272727272727,0.6079545454545454,0.6136363636363636,0.5795454545454546,0.5170454545454546 | |
GPT4o_0513,0.7159090909090909,0.6941558441558444,0.7048646724637749,0.7613636363636364,0.7670454545454546,0.6988636363636364,0.6988636363636364,0.7045454545454546,0.6761363636363636,0.7045454545454546 | |