model,prompt,eng,fra,eng ms,fra ms,aeb,afr,aka,amh,ary,arz,bam,bem,cjk,dik,dyu,ewe,fon,fuv,gaz,hau,ibo,kab,kam,kea,kbp,kik,kin,kmb,knc,kon,lin,lua,lug,luo,mos,nso,nus,nya,plt,por,run,sag,sot,sna,som,ssw,swa,tir,tso,tum,twi,tzm,umb,wol,xho,yor,zul,amh,hau,ibo,lin,lug,orm,pcm,run,sna,som,swa,tir,xho,yor,avg_score AfroLlama-V1,prompt_1,6.43,6.43,25.7,8.8,5.05,6.43,6.89,6.43,6.43,6.43,6.43,8.46,5.04,5.35,5.33,6.43,7.42,8.4,3.28,6.43,6.43,2.63,4.54,8.67,5.81,5.54,6.43,6.69,5.91,5.51,6.43,7.41,2.82,5.88,6.26,6.72,5.45,6,6.97,12.61,8.2,6.39,6.15,6.43,6.43,8.9,6.43,6.43,6.43,6.48,5.26,3.01,4.1,6.64,6.46,6.43,6.43,2.4,21.2,11.0,17.1,0.5,16.0,19.7,8.4,8.4,28.6,18.1,7.7,6.4,14.4,7.6 AfroLlama-V1,prompt_2,6.43,6.43,19.1,5.2,17.12,6.43,11.56,6.43,6.43,6.43,6.43,12.14,14.94,10,10,6.43,6.43,9.84,10,6.43,6.43,10.97,12.32,17.84,10,11.64,6.43,10.84,10.97,12.12,6.43,15.73,10.58,11.09,10,10.98,10.04,11.87,10.56,17.57,11.01,9.84,11,6.43,6.43,12.62,6.43,6.29,6.43,13.29,10.97,10,12.52,11.94,6.43,6.43,6.43,0.0,10.7,11.0,0.0,0.0,4.6,5.6,1.2,1.4,9.2,9.0,6.6,1.7,3.4,8.8 AfroLlama-V1,prompt_3,6.43,6.46,67.1,64.0,34.51,6.43,29.17,6.43,6.46,6.43,6.43,41.69,33.02,28.48,29.59,6.46,7.26,36.96,21.49,6.43,6.43,20.96,43.59,52.67,25.51,41.41,6.43,37.58,34.64,46.83,6.43,37.1,33.93,34.18,32.44,38.65,17.31,41.15,33.23,65.57,40.4,41.01,39.66,6.43,6.43,57.29,6.43,6.43,6.43,39.52,31.95,10.62,35.91,42.24,6.43,7.42,6.43,17.6,60.1,49.2,65.7,59.2,40.3,68.2,56.2,58.3,46.3,56.1,9.9,50.2,69.1,30.8 AfroLlama-V1,prompt_4,6.43,6.43,18.3,15.2,18.13,6.43,18.47,6.43,6.43,6.43,6.43,20.77,18.74,15.64,19.71,6.46,7.42,20.79,14.02,6.43,6.43,14.02,22.7,25.86,14.58,15.48,6.43,18.41,20.62,21.63,6.43,19.41,19.93,22,16.88,22.56,14.03,20.46,19.83,28.95,22.77,18.28,21.09,6.43,6.46,30.07,6.43,6.46,6.43,20.6,20.88,9.84,17.36,21.27,6.43,6.43,6.43,2.1,18.2,25.4,57.7,44.4,30.8,20.7,29.8,27.1,34.0,21.2,11.0,20.2,27.7,17.3 AfroLlama-V1,prompt_5,6.43,6.43,31.8,21.6,16.1,6.43,28.37,6.43,6.43,6.43,6.43,26.15,19.61,17.5,21.15,6.43,6.43,22.5,11.94,6.43,6.43,13.49,26.12,33.06,22.02,21.44,6.43,23.14,24.3,23.71,6.43,21.15,24.73,26.05,22.47,19.82,18.02,20.68,25.64,51.53,26.9,28.13,18.34,6.43,6.43,33.14,6.43,6.43,6.43,25.47,28.48,9.88,24.69,27.2,6.43,6.43,6.43,8.2,22.3,28.0,53.1,45.7,28.6,23.6,26.4,31.7,34.0,21.2,22.1,18.5,35.3,19.8 InkubaLM-0.4B,prompt_1,3.87,2.93,16.7,11.1,2.11,3.1,3.03,2.99,2.1,2.1,1.95,3.55,6.83,4.81,6.66,3,2.03,6.23,8.83,5.23,3.59,6.1,4.49,2.79,2.1,5.93,4.43,7.11,3.86,5.83,6.26,3.13,2.72,5.17,8.37,5.77,3,3.65,5.32,5.08,3,5.41,5.27,3.42,5.91,4,3.6,4.44,8.15,5.69,2.13,2.1,8.13,5.11,6.18,5.71,2.78,1.9,12.7,19.2,17.1,18.4,18.2,11.2,13.7,10.0,18.7,26.1,2.9,3.0,14.8,6.4 InkubaLM-0.4B,prompt_2,2.11,2.1,14.9,11.9,2.19,2.1,2.1,2.01,2.07,3.86,2.1,2.13,2.14,3.06,3.07,2.13,3.49,2.1,3.87,4.82,2.12,1.95,2.1,2.11,2.1,2.93,2.1,2.1,2.12,2.12,2.1,2.13,2.01,2.11,3.06,2.15,2.1,2.13,3.04,2.1,2.1,3.67,2.77,2.11,3.07,2.11,3.07,2.13,3.57,2.13,2.11,2.1,2.12,2.93,2.1,6.09,2.1,0.0,14.4,21.8,22.9,20.2,28.3,10.2,23.3,23.3,24.2,24.4,3.7,7.7,15.8,5.6 InkubaLM-0.4B,prompt_3,6.22,4.69,14.4,12.8,6.24,2.86,2.73,9.46,4.92,5.92,5.59,6.5,3.56,5.66,6.21,6.42,9.4,3.85,5.69,8.07,8.06,6,4.84,4.3,5.15,5.26,5.72,5.18,6.33,6.18,4.14,4.74,3.59,1.97,4.93,4.48,4.77,6.84,4.22,3.84,5.26,6.26,3.78,7.96,5.73,5.41,5.26,7.44,6.48,6.9,2.53,2.1,10.83,8.12,7.83,7.67,7.71,0.0,15.1,20.0,9.7,18.4,23.7,4.3,18.3,14.4,20.8,23.5,0.4,2.0,15.6,7.3 InkubaLM-0.4B,prompt_4,9.04,3.9,14.6,9.7,4.49,5.29,3.38,8.94,5.42,3.88,3.67,7.51,5.04,6.89,6.84,7.26,11.63,4.54,8.2,5.45,11.69,4.92,5.34,4.76,8.06,8.12,3.74,6.34,4.17,5.73,4.02,5.19,5.78,3.67,5.23,6.42,3.49,6.78,4.09,4.22,4.64,4.83,3.25,8.96,8.47,8.39,7,9.15,6.8,9.31,5.03,2.1,6.52,5.8,8.44,6.39,8.23,0.0,13.5,17.7,8.6,17.0,20.6,5.3,14.0,14.4,21.4,21.0,2.2,1.4,11.4,7.3 InkubaLM-0.4B,prompt_5,3.05,4.36,20.3,13.3,3.98,3.39,4.35,7.28,5.03,4.33,4.03,4.8,4.69,2.79,4.36,4.19,3.41,5.11,4.33,3.51,3.71,2.78,4.78,3.26,4.01,5.05,3.59,2.91,4.06,3.02,3.93,3.21,3.72,2.14,3.69,5.71,5.7,5.62,3.67,3.35,3.86,4.25,4.12,5.42,4.11,5.42,3.77,6.52,5.35,3.7,3.05,2.1,4.13,3.89,6.13,4.44,5.38,0.8,16.6,18.5,9.7,11.7,24.3,17.4,14.3,18.4,21.1,26.3,2.2,7.4,9.3,6.3 LLaMAX3-8B,prompt_1,10,10,23.5,9.5,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,16.8,18.7,2.8,30.9,1.4,7.1,14.8,15.8,4.3,9.5,13.0,15.1,11.5,7.5,10.4 LLaMAX3-8B,prompt_2,17.11,10.98,24.4,7.8,10,10.98,10,16.34,11.89,14.75,10.99,10,10,10,10,10,10,10,10.99,10.98,10.98,10,11.89,10,10,10,10.98,10,10.98,10,18.39,10,10,10,11.9,10,10,10.98,10,16.5,10,10,10.99,10,16.3,14.77,20.66,10.99,10,10,10.98,10.91,10,10.99,11.11,10,12.34,0.3,15.5,1.3,1.7,4.9,4.6,4.3,19.6,24.7,10.2,15.1,6.6,25.6,6.6,11.1 LLaMAX3-8B,prompt_3,77.18,77.16,61.3,49.1,68.27,75.87,48.11,39.15,70.27,67.69,29.65,47.36,35.86,40.33,35.95,41.16,31.28,36.37,38.46,67.44,68.62,21.11,44.61,67.6,33.56,44.64,69.52,37.07,40.39,55.16,59.53,50.61,52.39,37.94,36.38,55.49,26.99,67.69,70.65,67.26,65.45,43.95,58.82,66.96,63.02,61.33,75.54,27.59,53.72,60.11,49.31,3.77,32.62,54.08,71.72,57.02,73.58,35.1,47.6,43.3,75.4,49.8,40.0,52.1,42.2,39.6,37.1,41.8,42.3,45.8,44.5,49.8 LLaMAX3-8B,prompt_4,35.4,18.61,42.8,32.7,24.79,34.33,16.91,15.52,24.74,28.7,11.97,10.98,12.9,11.89,10.99,16.7,11.97,13.81,12.79,31.52,26.68,10,13.78,22.82,15.39,11.97,22.03,10,16.37,11.97,12.88,12.9,13.56,11.92,11.97,11.92,10.98,17.95,18.14,35.34,20.42,11.97,14.4,19.66,26.32,17.89,29.96,10.98,14.69,13.78,19.4,10,10,11.92,19.05,12.9,25.46,21.8,37.7,25.6,65.1,52.5,17.5,53.4,40.1,34.7,20.8,24.4,26.1,54.2,42.1,21.1 LLaMAX3-8B,prompt_5,48.34,22.73,31.8,23.0,41.35,60.75,22.9,21.92,42.3,48.66,21.2,13.72,17.92,21.71,17.25,15.64,15.27,24.17,29.6,37.66,33.11,14.81,18.32,25.3,15.39,21.34,36.39,14.54,27.56,23.59,15.81,20.03,17.28,16.8,17.98,33.09,13.78,20.39,34.58,44.88,31.95,14.77,32.94,21.96,40.79,39.91,45.37,19.56,28.2,20.61,26.72,10,13.54,19.37,25.03,20.74,43.45,16.2,25.0,8.2,58.3,38.1,9.5,26.2,28.9,19.5,10.2,13.9,18.4,22.9,17.5,25.1 Llama-2-7b-chat-hf,prompt_1,41.84,30.18,27.3,28.7,15.3,32.62,12.91,10,16.16,14.44,18.13,11.64,12.34,14.64,13.58,12.05,11.98,17.06,11.14,13.53,10.91,9.92,14.9,19.02,12.94,14.43,11.98,12.32,13.08,16.75,13.29,15.12,13.5,13.96,12.16,13.21,14.57,13.54,17.74,33.22,12.5,12.45,12.81,13.48,12.38,11.89,20.37,10.99,11.37,11.95,11.16,11.9,13.84,13.59,11.24,11.63,13.33,26.6,18.5,20.3,17.1,31.8,28.9,15.1,25.8,26.6,35.4,18.9,36.0,16.8,20.0,16.3 Llama-2-7b-chat-hf,prompt_2,49.15,45.87,21.6,14.0,13.64,37.8,12.8,3.52,10.23,15.78,9.25,7.67,13.15,11.9,19.13,17.49,7.14,14.57,2.92,10.85,14.97,2.22,12.03,25.61,2.24,21.54,10.74,10.1,3.91,16.96,13.17,16.63,10.35,15.88,15.27,7.4,8.78,21.07,9.32,35.68,14.65,14.75,5.8,15.77,6.95,8.68,14.06,1.28,8.29,13.61,16.25,2.25,8.77,11.45,16.29,7.28,13.58,2.1,21.0,4.4,2.3,22.9,4.0,16.7,6.8,18.4,10.9,11.1,6.3,2.7,18.0,12.1 Llama-2-7b-chat-hf,prompt_3,24.86,23.29,22.4,28.7,6.31,12.44,6.66,5.16,5.39,10.59,4.87,6.66,6.63,4.19,7.5,8.65,4.84,4.96,5.56,6.35,6.69,3.71,6.14,10.94,5.41,6.9,4.29,4.2,5.11,6.7,6.96,5.72,5.28,5.72,6.99,5.83,4.88,6.28,6.14,12.49,5.3,9.33,5.61,6.6,5.56,5.87,5.97,5.12,4.67,5.05,9.91,4.32,5.74,7.29,6.28,7.46,6.88,25.3,15.4,25.1,10.3,22.9,16.3,16.7,25.8,30.1,35.4,20.0,27.6,12.1,16.1,9.5 Llama-2-7b-chat-hf,prompt_4,24.18,20.26,24.3,37.9,31.46,6.17,14.88,11.22,29.68,31.08,9.79,15.47,18.23,13.32,14.62,11.42,10.35,13.18,10.38,12.23,5.18,7.26,14.87,12.36,12.66,19.31,12.38,12.96,18.94,20.02,18.14,17.98,12.03,11.74,8.97,15.14,12.34,19.63,26.14,8.94,14.19,13.99,16.02,22.63,14.77,15.92,12.94,11.16,17.68,16.49,9.66,13.14,15.22,15.61,15.81,8.52,20.78,14.9,36.4,26.2,52.0,45.3,33.9,60.0,45.0,37.4,43.9,25.4,12.5,20.5,48.4,19.4 Llama-2-7b-chat-hf,prompt_5,45.54,40.07,20.4,28.7,40.95,21.69,21.7,16.9,41.43,41.27,14.3,25.1,21.06,21,19.63,18.96,14.05,24.05,12.73,14.35,23.15,10.64,20.9,20.02,14.19,27.86,18.42,10.29,16.6,28.85,24.13,18.53,22.04,15.92,11.57,19.5,14.65,24,21.98,32.74,11.71,24.29,14.27,20.06,11.48,14.99,17.67,15.76,14.89,21.49,27.76,9.72,14.7,13.46,16.28,20.52,13.26,23.4,18.5,20.5,11.4,26.0,15.7,8.2,13.0,28.7,24.5,14.3,9.2,8.1,10.5,19.1 Llama-3.1-70B-Instruct,prompt_1,69.08,76.19,67.4,61.4,55.98,55.93,36.61,41.94,56.38,58.95,31.56,31.24,27.7,28.38,31.43,29.92,32.66,27.19,31.63,35.51,37.13,21.7,29.05,51.23,38.39,31.97,40.04,28.29,34.06,33.67,32.44,30.79,29.87,26.91,28.35,32.11,24.11,33.44,39.86,78.82,33.2,28.29,36.78,32.95,40.07,33.29,46.06,30.04,33.32,32.08,38.25,12.84,26.3,36.64,34.28,29.89,34.41,53.2,38.3,63.6,65.1,48.9,44.6,76.7,58.1,35.2,47.6,49.0,52.6,42.4,73.7,39.1 Llama-3.1-70B-Instruct,prompt_2,88.29,88.68,75.2,69.4,81.84,85.58,46.25,26.48,84.51,82,34.74,43.81,39.78,40.48,38.54,32.44,30.56,42.21,36.88,64.65,62.33,17.92,36.88,71.16,35.92,45.93,56.46,35.82,41.89,52.91,53.38,41.31,48.14,41.65,36.42,44.97,27.26,52.85,57.92,85.27,44.86,42.18,46.35,45.03,43.33,36.43,75.48,14.25,42.75,48.81,49.68,5.69,36.55,50.16,48.1,39.82,49.76,59.0,62.5,73.3,72.6,54.7,60.0,87.2,73.9,45.3,67.7,69.5,48.5,52.2,87.4,50.6 Llama-3.1-70B-Instruct,prompt_3,86.93,88.38,83.3,79.2,86.03,85.48,50.54,68.41,87.24,84.63,36.3,50.23,31.72,31.9,39.28,35.47,30.04,46.41,30.7,75.61,68.94,13.27,37.89,79.89,46.06,50.24,74.06,36.51,40.03,56.97,58.29,37.56,58.52,33.37,32.36,55.82,27.76,59.96,44,86.79,59.81,37.79,54.45,59.05,63.39,45.79,85.23,51.12,49.69,52.07,59.51,4.92,31.13,58.32,65,53.03,57.34,84.6,79.6,86.2,79.4,74.4,72.6,94.8,87.9,69.9,72.1,79.2,71.0,68.4,89.8,57.7 Llama-3.1-70B-Instruct,prompt_4,85.1,84.73,70.9,68.3,73.75,72.65,39.24,44.4,74.63,76.98,25.86,29.44,24.66,29.41,23.79,26.11,26.29,26.66,33.37,42.55,51.42,17.26,27.48,61.32,33.25,40.16,40.32,20.39,31.79,38.34,33.7,27.24,34.33,25.22,24.5,33.61,26.4,39.01,41.04,82.68,31.26,32.94,39.65,30.81,40.39,26.53,58.58,32.5,28.88,34.73,43.41,5.47,19.29,37.39,39.26,38.17,35.16,69.4,64.7,72.3,74.9,61.0,63.7,88.9,81.1,49.9,65.3,68.1,64.3,64.3,87.1,44.0 Llama-3.1-70B-Instruct,prompt_5,76.81,81.88,84.5,79.4,54.68,59.98,35.04,28.99,58.52,60.28,34.24,33.91,28.98,31.51,33.17,33.83,30.45,32.38,27.21,48.5,48.37,22.2,30.18,45.55,34.79,29.13,40.17,26.05,36.22,36.89,32.76,29.89,28.48,29.17,25.05,36.78,24.93,30.96,36.7,75.6,34.82,33.4,38.2,35.25,46.05,28.52,51.14,17.08,29.57,27.31,37.68,10.79,24.75,35.32,39.67,35.9,37.06,72.3,72.8,79.7,80.6,61.0,72.9,93.8,83.2,58.3,73.8,74.8,62.1,64.0,88.6,43.8 Llama-3.1-8B-Instruct,prompt_1,12.75,10.98,54.1,43.1,21.02,15.33,17.28,12.92,19.81,19.66,13.74,12.65,10.8,11.65,10.99,17.29,15.32,11.03,14.63,24.15,16.02,10,11.08,11.99,12.93,13.59,18.56,10.16,10.99,11.97,10.04,10,19.77,12.84,10,10,9.76,11.83,10.99,17.57,18.96,10.98,10,14.93,12.75,10,16.31,11.52,10.98,10.86,18.11,10,10.98,11.97,10,13.78,11.92,0.0,31.6,36.2,52.6,40.8,14.5,56.1,42.6,27.6,35.7,41.4,6.6,26.9,21.9,17.1 Llama-3.1-8B-Instruct,prompt_2,62.57,73.93,72.2,72.3,75.32,76.65,46.16,36.57,78.02,73.39,37.4,36.6,39.53,34.71,36.01,33.81,33.97,33.36,39.75,57.65,43.95,26.4,28.11,73.39,36.85,37.54,49,38.06,40.1,49.12,47.23,43.24,39.08,34.62,34.42,48.77,25.74,44.77,47.31,80.39,41.9,38.41,47.92,42.71,49.12,45.3,66.19,17.84,42.69,44.48,49.9,10.04,36.77,53.77,45.45,45.85,48.89,33.8,55.0,71.5,69.1,47.5,35.4,84.3,72.1,45.5,60.5,65.6,25.0,30.0,72.5,46.7 Llama-3.1-8B-Instruct,prompt_3,79.32,80.31,75.7,77.7,67.8,80.8,43.6,54.54,74.01,70.06,27.97,36.95,20.13,24.56,28.25,31.86,32.34,34.43,20.27,69.93,62.37,7.51,40.28,65.34,32.29,33.38,64.51,18.33,24.27,37.86,43.89,27.48,49.03,37.09,20.78,28.8,24.3,48.74,32.84,78.76,46.31,40.07,38.45,50.82,48.6,28.91,73.48,28.07,35.97,50.51,54.66,2.26,22.75,51.53,52.8,49.42,44.73,52.4,70.8,74.1,78.9,58.3,45.2,87.2,79.5,56.4,59.5,75.2,27.9,44.8,79.8,46.3 Llama-3.1-8B-Instruct,prompt_4,72.11,62.84,68.3,70.1,58.67,63.25,39.22,43.78,62.54,57.74,35.02,42.76,30.11,28.58,32.11,31.8,28.07,30.35,34.54,57.33,48.69,23.96,34.63,60.39,41.34,42,47.09,31.48,39.37,39.69,39.72,36.27,45.05,34.72,29.61,42.61,25.54,49.48,49.4,70.48,47.67,34.38,43.9,47.83,43.15,45.69,62.53,19.95,47.03,42.13,43.94,12.18,31.44,45.36,51.19,37.99,51.87,52.9,64.2,66.7,71.4,49.3,40.3,86.6,78.6,46.9,56.1,70.6,18.0,41.8,84.9,45.4 Llama-3.1-8B-Instruct,prompt_5,67.26,50.26,67.9,73.0,36.01,56.7,32.16,24.5,35.31,34.2,20.88,23.02,21.92,20.6,30.86,26.8,22.39,24.75,24.87,39.18,40.95,12.94,21.94,35.18,24.31,23.77,30.88,20.32,24.4,27.25,25.25,29.14,31.74,26.67,22.7,25.95,16.34,27.22,21.04,37.12,30.83,24.8,24.89,25.6,30.54,26.2,35.75,13.84,24.62,23.59,29.93,9.88,24.37,28.87,24.78,25.91,20.79,53.2,53.5,61.5,59.4,55.6,35.1,68.5,67.4,49.3,51.4,64.9,16.9,28.6,53.8,32.0 Meta-Llama-3-8B-Instruct,prompt_1,16.37,10,42.3,32.9,10,10,10,10,10.99,10.99,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,11.7,20.3,16.2,4.0,15.3,16.3,31.8,23.9,4.6,24.5,37.4,14.0,24.9,14.6,11.8 Meta-Llama-3-8B-Instruct,prompt_2,77.92,77.56,41.8,50.5,63.91,53.09,39.46,11.92,67.27,68.82,33.48,37.1,30.26,30.75,30.38,28.48,21.58,30.66,21.53,46.87,43.32,20.79,33.17,55.13,22.82,38.04,45.72,29.66,31.55,42.11,44.78,34.85,34.19,30.63,34.59,36.07,24.54,39.9,18.52,79.04,42.36,35.03,38.78,42.73,44.22,39.99,66.28,11.92,32.83,37.8,38.8,10,30.25,43.36,33.35,30.54,40.03,0.0,48.7,22.3,53.7,41.7,12.3,42.6,34.5,36.9,25.5,43.7,6.6,34.3,20.0,35.8 Meta-Llama-3-8B-Instruct,prompt_3,77.87,74.54,68.8,75.8,58.7,70.31,32.89,27.82,63.1,63.78,23.61,23.86,20.92,23.4,17.61,30.6,26.52,23.66,13.57,53.7,36.04,14.81,25,49.04,22.58,23.41,47.93,19.45,15.45,33.15,31.75,25.13,24.72,30.54,22.53,17.5,16.34,26.91,15.62,76.22,19.81,30.92,24.6,32.73,29.87,17.17,66.79,14.71,23.82,27.02,47.1,10.07,18.44,44.65,33.71,24.84,25.98,55.6,60.0,63.1,66.9,57.4,59.7,63.9,66.8,66.1,58.8,71.9,38.6,49.2,61.6,37.0 Meta-Llama-3-8B-Instruct,prompt_4,45.13,37.15,60.3,58.5,31.04,29.67,20.17,12,30.67,34.19,14.69,10.66,14.21,18.63,13.82,23.51,15.51,14.34,11.81,18.78,16.18,12.77,14.03,27.82,13.95,17.59,13.86,12.54,15.36,12.47,15.84,17.67,13.4,14.5,13.61,12.1,14.58,10.98,13.13,37.63,11.1,13.46,11.69,14.42,16.75,12.65,21.88,10.99,11.74,13.31,20.19,11.45,13.62,17.94,12.09,11.93,16.23,25.0,47.3,45.9,44.0,46.2,38.8,61.6,47.5,38.5,35.4,48.1,17.3,46.5,53.5,22.0 Meta-Llama-3-8B-Instruct,prompt_5,19.58,11.89,66.7,72.5,10,10,10,10,10,10,10,10,10,10,10,10.98,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,11.89,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,10,30.3,36.3,45.6,32.6,28.3,45.2,53.4,53.7,30.4,40.5,58.6,32.0,39.7,40.4,16.4 aya-101,prompt_1,80.66,82.26,87.1,80.8,82.54,83.68,67.96,79.58,80.8,83.35,53.1,66.5,47.62,38.79,51.19,56.99,39.68,50.86,68.11,81.6,78.64,26.22,48.72,83.55,41.68,55.93,77.82,49.76,53.78,62.47,67.09,56.39,59.81,53.9,43.23,80.57,37.21,80.61,84.03,82.43,80.09,59.69,81.41,80.12,80.71,74.79,79.84,78.29,68.65,73.61,71.89,21.06,45.17,57.59,80.76,71.65,80.84,88.3,82.6,79.0,83.4,84.8,89.2,95.4,92.9,79.1,70.8,79.4,81.6,94.6,93.9,69.2 aya-101,prompt_2,80.85,82.99,87.3,82.7,81.8,81.83,69.5,82.18,81.54,83.35,55.93,68.44,49.55,41.9,50.83,57.62,43.73,52.28,66.06,81.42,77.87,24.25,50.66,82.45,47.48,58.37,79.78,49.45,52.72,67,70.87,60.07,62.8,56.92,49.03,82.05,39.61,78.93,83.83,82.31,78.44,59.19,80.39,79.89,81.52,75.97,81.58,77.67,67.28,76.31,71.61,27.59,47.88,59.67,81.98,76.29,82.91,88.0,81.6,80.0,83.4,84.8,88.9,96.1,92.6,78.9,74.5,80.7,82.0,93.6,94.2,70.3 aya-101,prompt_3,82.13,80.97,86.0,76.5,76.79,79.7,66.62,75.97,76.2,76.8,51.62,63.48,45.13,38.82,48.85,55.93,43.41,49.23,64.68,79.98,78.92,26.44,49.33,77.64,47.08,54.85,77.98,47.37,52.36,61.1,67.48,55.94,57.75,54.54,44.5,78.94,35.99,77.82,77.46,79.81,73.61,56.78,79.57,79.94,80.46,71.4,78.08,74.07,65.55,69.19,72.34,25.43,42.55,55.67,76.99,71.29,82.57,87.8,81.6,80.0,82.9,83.0,91.1,94.4,92.9,76.2,70.4,79.8,80.2,94.3,94.4,67.8 aya-101,prompt_4,82.82,81.4,78.1,69.7,79.46,82.96,72.28,79.66,82.88,83.59,54.32,67.07,49.92,45.37,53.74,54.23,45.81,50.83,67.52,82.8,82.05,35.82,55.71,81.26,51.82,61.31,79.18,55.36,56.55,66.3,69.68,56.71,62.89,57.7,48.23,80.23,41.62,81.54,85.34,83.61,78.6,57.9,80.6,82.39,81.99,76.73,79.91,79.03,70.23,74.14,70.49,26.52,49.81,58.3,80.49,76.54,80.76,78.5,78.8,71.5,81.1,79.4,91.1,91.5,91.0,68.8,70.4,73.3,78.3,91.9,93.9,70.0 aya-101,prompt_5,77.54,76.17,86.1,77.5,77.05,76.92,68.18,75.69,74.05,76.4,52.5,62.67,46.38,43.03,48.41,54.98,40.19,50.12,64.15,78.72,75.03,28.96,49.07,75.32,43.21,56.09,77.27,50.97,52.28,63.32,67.49,54.6,61.02,52.54,42.64,76.91,32.33,79.99,80.16,76.63,73.93,54.59,77.12,76.78,77.5,71.96,76.41,72.64,62.4,69.94,70.59,25.38,46.22,57.48,75.45,73.48,75.1,88.8,83.2,78.5,85.1,84.3,88.0,96.7,94.7,78.6,71.4,80.0,80.2,95.3,93.2,67.5 gemma-1.1-7b-it,prompt_1,74.08,65.71,25.3,12.6,69.04,68.19,41.26,18.06,65.63,65.21,34.8,41.9,33.81,35.44,33.77,35.55,30,38.39,30.1,38.49,42.01,23.41,36.8,61.05,32.16,43.22,33.23,35.13,43.64,39.64,38.51,35.63,31.73,37.61,37.18,36.02,27.09,44.24,40.63,69.2,32.81,34.97,38.29,38.48,36.46,31.87,54.53,13.65,35.69,40.47,41.1,13.66,33.99,44.05,40.91,32.28,37.09,1.9,15.9,6.2,4.0,4.5,4.6,5.3,3.1,3.3,8.8,9.0,7.4,3.7,4.1,32.1 gemma-1.1-7b-it,prompt_2,81.05,78.77,68.1,64.2,64.54,67.02,39.48,18.61,62.68,66.79,29.97,42.22,32.74,34.08,31.18,28.36,24.53,39.29,30.32,46.74,40.02,16.12,37.8,62.05,30.15,41.71,35.92,30.92,34.64,41.15,40.7,42.05,35.87,34.35,38.57,41.94,26.27,44.36,42.47,76.15,33.33,36.28,41.7,35.92,34.55,34.81,59.87,12.8,33.68,41.25,39.04,2.54,35.31,44.47,46.83,28.18,42.43,28.5,71.1,69.0,79.4,61.4,75.4,86.9,86.3,71.8,68.4,72.5,34.2,81.5,84.4,45.2 gemma-1.1-7b-it,prompt_3,86.28,73.35,71.4,38.9,33.23,52.49,28.21,13.88,32.26,43.15,20.5,24.28,25,17.49,23.13,19.45,17.14,16.12,15.75,31.33,28.82,11.89,25.76,33.12,21,21.46,25.28,18.68,22.33,24.82,24.48,26.78,23.48,29.58,20.54,24.81,15.16,28.89,25.64,65.32,24.73,23.45,22.58,27.75,29.84,30.07,43.82,12.07,26.62,22.68,27.29,10,17.37,26.72,27.4,25.32,24.79,10.1,40.2,20.8,17.1,4.5,20.6,51.2,33.2,25.2,27.9,26.9,9.6,24.9,41.4,25.5 gemma-1.1-7b-it,prompt_4,75.74,74.41,69.9,50.0,71.73,75.24,42.26,23.06,71.88,71.91,37.72,44.17,37.36,37.97,44.97,36.62,27.57,43.61,33.31,46.14,48.81,24.39,43.06,69.56,34.7,42.03,38.73,33.65,44.59,46.62,43.53,43.63,38.66,40.93,38.29,39.99,29.11,46.61,49.4,74.33,35.51,41.09,44.56,38.2,39.53,36.36,57.04,15.47,38.56,40.84,40.95,13.41,30.96,51.05,50.62,33.45,41.19,32.7,59.7,52.3,70.3,57.9,45.9,80.0,58.1,48.0,50.0,54.2,24.6,70.4,66.4,45.3 gemma-1.1-7b-it,prompt_5,82.64,76.74,66.2,29.9,55.8,73.3,32.28,12.86,57.54,62.57,22.9,33.67,22.94,33.77,30.12,23.57,25.16,22.02,23.09,35.34,29.16,15.38,31.54,60.16,27.93,28.83,38.76,22.74,28.96,33.49,37.81,38.25,35.57,22.91,21.36,32.8,21.86,35.25,37.94,77.48,27.54,28.82,37.45,30.97,33.13,31.6,60.4,11.98,30,28.32,33.59,10,19.33,33.08,30.26,23.11,25.72,0.3,24.0,16.2,11.4,6.7,6.5,55.1,7.8,17.3,16.3,19.1,6.6,14.8,14.8,29.2 gemma-2-27b-it,prompt_1,84.21,82.89,79.1,74.6,80.72,83.02,59.15,71.81,82.05,82.88,39.52,52.11,39.92,42.26,43.78,39.73,36.94,40.96,44.96,71.43,73.65,25.98,44.08,75.75,45.79,54.9,66.52,36.31,39.94,54.5,50.92,47.49,51.9,39.54,37,56.56,34.37,64.01,65.31,83.81,55.67,40.62,64,58.67,68.72,56.83,81.49,58.11,53.37,57.57,63.66,10.16,38.83,49.18,67.96,61.23,68.05,76.6,74.9,75.1,80.0,72.2,79.1,90.5,85.1,71.0,74.2,76.5,66.9,87.2,88.3,59.9 gemma-2-27b-it,prompt_2,89.33,89.33,81.9,65.9,82.3,87.55,55.52,74.44,83.92,81.81,38.54,55.99,41.44,42.33,46.68,39.91,34.87,45.35,32.33,74.75,72.86,22.1,46.92,80.73,42.66,55.87,68.01,39.31,42.75,55.48,54.69,43.86,56.47,47.93,40.11,60.87,33.44,58.4,59.21,88.81,56.79,46.34,65.95,61.95,63.75,57.45,85.42,53.89,57.03,56.71,61.57,7.19,41.39,56.42,70.28,62.5,69.26,73.7,77.2,62.8,80.0,77.6,80.9,91.8,87.0,66.9,73.5,72.7,69.9,91.3,87.1,60.5 gemma-2-27b-it,prompt_3,82.2,82.89,80.2,77.7,80.68,82.59,58.28,75.01,83.34,83.35,40.62,60.73,38.22,37.51,48.91,40.74,34.3,47.06,37.41,71.7,75.16,27.78,44.57,81.87,45.85,56.25,74.4,43.53,46.64,56.41,55.34,43.4,54.24,39.74,35.39,65.65,30.9,64.68,63.43,83.44,62.94,43.69,67.58,72.62,70.21,55.52,85.63,61.66,56.35,65.13,65.04,10.53,45.01,56.93,71.63,62.17,72.55,79.5,80.7,84.6,85.1,78.9,81.2,92.1,89.1,77.2,75.2,79.0,73.9,85.9,85.6,62.4 gemma-2-27b-it,prompt_4,82.19,82.48,70.2,70.4,76,79.98,44.2,66.69,75.8,80.57,33.77,43.25,25.3,29.51,26.12,28.63,25.87,27.47,36.21,67.83,66.86,19.19,33.4,67.01,32.92,42.94,63.7,25.46,24.17,40.98,45.38,38.22,43.65,24.28,19.67,56.09,22.18,62.98,63.94,78.97,52.64,29.82,59.34,53.53,64.3,51.33,77.51,54.12,48.66,50.68,51.39,7.83,25.58,38.94,64.15,49.39,65.02,71.8,73.2,76.2,80.0,70.0,78.5,87.9,85.7,66.7,70.4,71.6,71.0,87.9,87.8,53.2 gemma-2-27b-it,prompt_5,83.94,85.1,78.5,75.6,77.92,82.8,59.15,73.5,76.74,80.9,44.78,57.09,39.15,39.09,49.91,42.59,40.04,38.78,43.23,74.18,74.24,31.14,44.12,79.42,44.85,48.4,67.49,42.91,42.07,56.7,55.27,44.9,46.98,40.68,35.9,57.73,30.5,66.61,66.13,83.4,57.28,44.72,64.31,66.92,71.08,58.33,82.91,59.7,51.74,61.25,60.56,13.88,44.27,53.87,69.6,60.52,69.39,79.3,80.2,82.8,83.4,78.0,78.5,90.8,86.0,78.1,73.5,77.9,71.0,86.5,86.6,61.2 gemma-2-9b-it,prompt_1,82.54,84,82.0,75.8,75.16,78.12,48.28,59.48,75.63,76.07,39.54,48.72,42.95,35.53,35.29,35.1,37.48,38.39,38.05,69.87,60.17,22.59,37.74,68,35.55,45.05,57.98,36.64,46.22,45.71,47.18,45.18,48.8,39.9,39.41,49.58,26.77,67.09,51.25,81.71,48.52,44.38,53.81,60.04,60.72,51.23,76.28,40.41,46.35,56.28,53.69,4.87,35.96,51.59,63.24,50.2,59.84,78.7,73.9,79.5,75.4,60.5,60.6,92.5,83.9,65.3,72.8,80.9,56.3,58.6,88.3,54.8 gemma-2-9b-it,prompt_2,76.35,77.86,85.4,76.3,75.22,74.7,45.6,59.41,72.84,76.89,31.33,43.8,34.14,31.56,37.71,34.27,27.94,39.62,29.58,61.84,55.18,12.93,35.56,72.08,34.52,46.61,53.81,32.78,34.05,47.94,48.9,35.35,48.19,36.25,33.51,44.67,24.56,47.24,47.09,79.69,44.69,35.31,48.05,50.33,49.14,42.25,71.87,43.71,37.86,47.78,48.16,7.06,35.85,47.43,54.81,48.17,56.17,80.9,79.1,83.3,82.9,67.3,64.3,94.8,85.1,70.7,72.1,81.9,56.6,64.7,91.5,52.1 gemma-2-9b-it,prompt_3,80.27,75.66,81.3,78.9,67.05,72.88,34.88,52.74,69.31,64.75,26.62,31.68,19.28,16.63,29.72,26.87,21.27,24.05,5.89,52.65,37.59,9.68,32.88,54.62,27.48,30.26,47.25,18,16.33,41.33,37.69,22.64,33.52,33.62,21.15,23.99,11.32,42.06,28.32,75.42,43,23.63,42.84,49.46,46.7,32.27,65.05,29.37,24.39,28.58,45.49,2.25,22.73,31.84,50.35,35.65,58.16,81.4,80.4,86.2,82.3,66.8,74.2,92.5,89.8,75.3,76.5,80.3,69.1,67.0,89.3,44.8 gemma-2-9b-it,prompt_4,78.28,79.94,71.5,66.6,77.24,75.9,43.97,61.83,76.09,79.81,26.96,43.53,29.67,30.67,28.21,26.41,20.84,29.89,37.29,66.63,59.89,11.4,29.21,75.45,31.38,40.74,61.62,23.98,33.67,42.17,44.78,34.05,45.81,32.37,26.76,50.88,14.65,65.46,56.62,80.71,44.04,30.87,56.47,53.31,59.98,47.7,73.79,49.6,40.73,45.14,54.12,2.2,27.69,43.5,58.38,50.45,61.09,67.8,71.9,72.8,62.3,56.1,53.9,89.5,81.7,49.6,67.0,71.2,53.7,62.3,87.4,50.2 gemma-2-9b-it,prompt_5,81.94,82.13,66.9,76.5,79.34,79.46,55.33,67.16,79.24,82.17,38.32,53.31,45.61,47.25,47.1,43.98,32.37,45.92,41.9,68.55,70.21,28.11,45.47,78.15,43.92,54.44,68.34,41.92,39.25,56.99,52.94,50.93,55.69,52.54,39.35,57.69,28.56,68.83,60.19,81.01,58.09,47.21,65.08,65.71,67.33,57.08,79.59,55.32,57.61,64.5,61.6,5.72,42.12,56.2,67.31,65.66,71.33,62.0,70.5,59.2,40.6,32.3,46.8,81.6,57.8,59.9,53.1,69.1,33.1,51.9,62.0,56.0 gemini-1.5-pro-002,prompt_1,86.27,86.76,84.8,79.4,84.8,86.27,76.96,87.75,87.75,84.8,42.65,63.73,26.96,32.35,29.41,58.33,49.51,24.51,60.78,82.84,82.35,43.63,47.55,82.84,55.88,68.63,81.37,33.33,29.41,69.12,74.51,50.98,73.04,36.76,25.49,79.9,26.47,86.27,85.29,87.25,79.9,50.98,83.82,85.78,79.9,72.06,34.31,80.39,73.04,79.41,79.17,36.27,42.65,42.16,84.31,75.49,83.82,88.0,80.1,83.9,82.3,75.8,78.2,94.8,89.0,71.0,83.2,80.7,80.2,77.1,91.5,67.4 gemini-1.5-pro-002,prompt_2,88.24,89.22,84.2,80.3,84.8,88.73,78.92,87.25,87.25,83.82,59.8,82.35,52.94,49.02,55.39,70.1,57.84,59.31,76.47,85.29,85.29,55.39,60.29,86.76,58.82,72.55,85.29,61.27,51.96,76.47,85.78,70.1,79.9,57.35,48.53,86.27,37.25,85.29,87.75,88.73,83.33,67.16,88.73,83.33,81.37,81.86,54.9,85.78,82.84,82.35,81.62,39.22,59.8,62.25,89.71,79.41,88.73,89.4,81.8,86.7,85.1,79.8,86.5,95.4,91.0,76.4,81.0,80.7,83.5,81.8,92.2,75.6 gemini-1.5-pro-002,prompt_3,88.73,90.2,85.2,79.2,86.27,85.78,78.43,87.25,86.76,88.24,61.27,82.35,53.43,43.63,60.78,71.57,57.35,59.31,78.43,87.25,81.86,57.84,64.22,86.27,66.67,74.51,84.31,65.69,55.88,76.47,85.29,66.67,78.43,57.35,49.51,84.31,30.39,83.82,85.29,88.73,83.33,67.16,85.78,85.29,83.82,78.92,57.35,82.84,80.88,81.37,81.86,39.22,65.69,62.75,85.78,79.9,86.27,87.0,80.2,83.3,83.4,78.0,80.0,92.8,91.0,70.7,81.6,81.1,83.8,78.1,91.7,75.3 gemini-1.5-pro-002,prompt_4,87.75,88.73,73.6,71.1,84.8,87.25,77.45,86.27,85.78,86.27,50.98,77.45,49.02,50,50,70.1,57.84,49.51,73.04,84.8,81.86,51.96,62.25,87.25,64.71,71.08,81.86,55.88,50.98,74.51,81.86,64.22,74.51,53.43,45.1,81.37,42.65,83.82,85.78,87.75,78.92,64.22,83.82,82.84,81.86,79.41,53.92,81.37,80.39,78.43,81.37,42.16,56.37,63.24,85.29,80.88,83.33,75.5,75.4,77.2,79.4,73.5,80.9,89.8,86.3,61.5,77.9,75.2,80.5,74.4,90.0,72.5 gemini-1.5-pro-002,prompt_5,88.73,89.71,82.0,78.7,87.25,87.25,80.39,87.25,87.75,87.25,60.29,80.39,56.86,53.92,60.29,73.04,60.78,60.78,81.37,85.78,81.86,57.84,63.73,87.25,68.14,74.02,84.31,66.18,50.98,79.41,87.75,70.59,78.92,56.86,51.96,86.27,46.08,83.33,85.29,89.22,81.37,72.55,86.27,83.33,86.76,80.39,59.8,82.84,81.37,81.86,82.35,45.59,61.27,63.24,86.27,85.29,86.76,89.4,82.6,87.2,84.6,78.9,85.9,94.4,91.0,75.3,81.3,80.0,84.6,84.2,89.5,76.7 gpt-4o-2024-08-06,prompt_1,89.05,86.76,83.0,80.3,86.76,90.2,76.47,84.31,87.25,86.76,54.41,75.98,48.04,47.55,51.47,51.47,40.2,58.33,81.86,86.76,84.31,43.63,67.16,88.24,41.67,72.55,85.78,51.47,49.02,72.06,87.25,64.71,80.39,72.06,43.14,86.76,33.82,87.75,87.25,86.76,82.84,54.41,84.8,85.29,83.33,81.86,53.43,75.49,84.8,80.88,77.45,14.71,55.39,73.04,85.78,84.31,84.8,85.4,78.2,82.8,83.4,78.0,83.4,94.8,90.4,70.7,78.7,77.3,77.2,80.5,92.2,73.0 gpt-4o-2024-08-06,prompt_2,89.22,90.2,82.4,79.4,89.22,88.73,78.43,86.27,88.24,88.24,56.37,77.45,50.98,50.49,55.39,51.96,43.14,61.76,87.25,86.76,83.82,36.27,69.61,85.29,48.04,73.04,87.75,48.53,50.98,76.96,83.33,60.78,79.9,73.04,47.55,86.76,41.18,84.8,84.31,87.75,82.35,59.8,85.29,84.8,84.8,83.33,49.02,79.41,83.82,86.27,77.45,12.25,56.37,77.94,87.25,81.37,89.22,87.2,82.9,85.6,85.1,81.2,88.3,95.7,91.3,74.8,81.0,80.9,84.6,85.2,92.7,74.4 gpt-4o-2024-08-06,prompt_3,88.24,88.24,83.2,80.6,87.25,87.75,76.47,85.78,88.73,86.27,57.84,76.96,54.41,47.55,59.8,51.96,45.59,64.71,85.78,85.29,83.33,50.49,73.04,86.27,47.55,75.49,84.8,53.43,57.35,77.45,86.27,61.76,81.37,78.92,43.63,86.27,46.08,84.8,77.45,88.73,85.29,56.86,83.82,86.27,85.78,83.33,58.33,80.88,85.78,81.37,77.94,12.75,59.31,79.9,87.75,85.29,87.75,86.7,80.4,83.9,85.7,79.4,85.2,94.4,89.8,71.3,79.9,80.0,78.3,80.8,93.2,74.8 gpt-4o-2024-08-06,prompt_4,89.22,88.24,75.7,74.9,88.73,87.75,77.45,88.73,86.76,87.75,54.41,75,46.57,44.61,48.53,48.04,38.24,56.86,84.8,84.8,81.86,38.73,69.12,85.29,41.67,75,86.27,44.12,47.06,75,84.8,61.27,78.92,67.65,43.63,85.78,37.75,85.29,85.29,87.25,84.8,50.49,83.82,84.31,84.8,82.11,51.47,78.43,82.35,82.84,78.92,12.75,50.98,74.51,86.76,85.29,86.27,77.7,76.9,80.0,76.0,74.0,80.9,91.5,85.1,64.8,73.5,75.2,72.1,74.1,91.5,71.6 gpt-4o-2024-08-06,prompt_5,84.31,86.27,82.0,78.2,84.8,84.31,75,81.86,86.76,83.33,59.31,75.49,48.53,46.08,55.88,47.06,45.1,60.78,80.88,82.84,81.37,43.14,70.59,87.25,44.61,72.06,84.31,44.61,49.02,74.51,82.35,61.76,77.45,70.1,45.1,83.33,40.69,83.33,81.86,85.29,76.96,57.84,80.88,81.37,82.35,76.96,50,75,81.86,82.35,73.04,15.69,52.94,72.55,83.82,78.92,82.35,87.5,82.7,85.4,88.6,80.7,88.0,95.7,90.1,78.1,79.9,77.7,78.7,85.9,90.8,72.5