Spaces:
Running
Running
| models, North America,South America,East Europe,South Europe ,West Europe,Africa,Middle East/ West Asia,South Asia ,Southeast Asia,East Asia,Oceania | |
| gpt-3-5-turbo-1106 ,80.72,71.34,72.64,83.75,78.61,81.22,54.71,80.68,67.5,63.7,86.36 | |
| gpt35turbo ,87.85,72.21,76.86,80.97,74.61,80.74,59.19,83.82,68.39,62.04,78.48 | |
| gpt4omini ,90.35,78.54,89.08,89.16,87.31,87.24,71.4,90.46,81.2,79.14,87.57 | |
| gpt4o ,100,87.82,91.93,91.66,97.22,91.81,80.78,90.13,86.07,86.44,92.12 | |
| gpt-4o-2024-08-06 ,100,85.61,92.32,93.06,97,92.42,86.76,90.22,86.28,88.5,92.12 | |
| gpt-4-0125-preview ,100,86.9,90.96,90.42,94.44,87.97,82.34,94.11,85.46,84.7,87.57 | |
| gpt-4-1106-preview ,97.5,87.22,92.28,91.8,90.65,85.59,82.5,95.65,84.95,85.6,96.66 | |
| haiku ,80.35,58.8,64.91,67.91,55.78,72.39,58.07,68.76,57.09,56.52,76.37 | |
| sonnet3 ,68.22,59.53,64.76,64.16,56.56,60.68,58.91,67.34,62.31,54.51,57.28 | |
| opus ,100,74.56,81.16,84.86,83.96,83.13,73.58,88.64,80.1,79.47,92.12 | |
| sonnet35 ,95,76.45,76.7,82.36,82.74,80.64,77.01,85.68,77.95,80.98,88.79 | |
| mistralnemo ,80.72,69.46,78.49,74.86,72.83,77.66,62.26,79.63,71.68,64.82,80.91 | |
| mistralsmall ,73.22,64.58,73.46,72.36,70.05,77.91,56.36,71.89,66.32,62.75,75.16 | |
| mistral-large-2402 ,63.57,56.19,64.19,61.94,55.78,62.71,41.14,63.52,60.79,50.95,42.72 | |
| mistrallarge ,95,82.87,88.18,93.2,86.53,88.9,79.13,88.68,82.45,84.77,92.12 | |
| llama3-8b ,80.35,66.7,73.79,74.86,66.83,78.02,57.75,78.06,76.04,60.07,71.82 | |
| llama3-70b ,97.5,78.54,87.9,87.64,85.74,85.37,75.94,86.34,85.66,78.65,79.7 | |
| llama3-1-8b ,85.35,69.87,73.92,70.84,70.4,77.77,58.46,84.07,74.86,62.38,69.7 | |
| llama3-1-70b ,97.5,76.29,88.43,87.78,86.53,83.02,76.98,91.65,87.39,80.15,92.12 | |
| llama3-1-405b ,100,80.23,85.31,86.11,88.31,88.8,80.97,89.56,84.36,88.24,87.57 | |
| gemma2-9b ,87.85,70.11,82.81,86.53,78.96,81.18,68.54,81.08,78.52,67.92,76.37 | |
| gemma2-27b ,87.85,72.66,84.63,85,84.31,85.03,69.07,90.59,80.03,71.28,76.37 | |
| mistral-7b-v1 ,61.43,53.36,57.2,56.25,58.92,68.35,49.33,63.76,60.71,55,56.06 | |
| mistral-7b-v2 ,73.22,51.56,55.45,57.64,54.14,66.8,43.44,58.6,54.08,47.24,60.61 | |
| mixtral-8x22B ,80.72,69.83,78.36,80,75.4,81.04,64.61,83.49,74.98,68.13,76.37 | |
| qwen1-5-72b-chat ,97.5,74.54,85.48,90.56,82.18,83.03,71.01,88.01,81.32,76.98,80.91 | |
| qwen2-72b ,97.5,81.45,86.94,86.39,89.87,85.78,69.86,87.59,78.14,83.03,95.46 | |
| random ,24.28,29.85,22.76,26.39,32.39,28.26,25.32,20.8,25.59,22.9,25.76 | |
| human ,91.65,92.27,93.6,92.92,92.31,91.65,92.53,94.48,93.47,92.08,90.06 |