Grado,2,2,5,5,5,5,5,6,6,6,8,8,8,10,10,10,10,13,13
Type,MC,MCC,CL,MC,MCC,RB,RU,MC,MCC,RU,MC,MCC,RU,CL,MC,MCC,RU,MC,MCC
Model,,,,,,,,,,,,,,,,,,,
Italia-9B-Instruct-v0.1,53.1,0.0,0.0,43.3,0.0,0.0,33.3,38.0,0.0,11.1,44.4,0.0,0.0,0.0,45.8,7.7,21.4,45.2,0.0
LLaMAntino-3-ANITA-8B-Inst-DPO-ITA,71.9,0.0,0.0,70.0,14.3,0.0,16.7,67.6,42.9,22.2,55.6,100.0,50.0,0.0,64.6,23.1,57.1,45.2,0.0
Llama-3-8b-Ita,78.1,0.0,0.0,75.0,14.3,0.0,33.3,67.6,42.9,44.4,59.3,0.0,50.0,0.0,66.7,15.4,50.0,61.9,0.0
Llama-3-COT-ITA,56.2,0.0,0.0,43.3,0.0,0.0,16.7,38.0,0.0,33.3,39.5,0.0,0.0,0.0,43.8,7.7,21.4,28.6,0.0
Llama-3.1-8b-Ita,81.2,0.0,0.0,78.3,28.6,0.0,16.7,69.0,42.9,11.1,67.9,0.0,0.0,0.0,68.8,15.4,57.1,61.9,0.0
Minerva-3B-base-v1.0,0.0,0.0,0.0,13.3,0.0,0.0,0.0,0.0,0.0,0.0,8.6,0.0,0.0,0.0,6.2,0.0,0.0,4.8,0.0
Minerva_3B_Ties_1.0,6.2,0.0,0.0,28.3,0.0,0.0,0.0,32.4,28.6,11.1,39.5,100.0,0.0,0.0,47.9,7.7,7.1,42.9,25.0
claude-3-haiku,100.0,50.0,0.0,91.7,28.6,0.0,33.3,84.5,57.1,77.8,85.2,100.0,75.0,50.0,75.0,46.2,64.3,71.4,12.5
claude-3-opus,100.0,100.0,100.0,98.3,71.4,100.0,33.3,93.0,85.7,88.9,93.8,0.0,100.0,50.0,85.4,61.5,71.4,90.5,25.0
claude-3-sonnet,100.0,100.0,100.0,96.7,85.7,100.0,50.0,88.7,57.1,66.7,87.6,0.0,75.0,50.0,81.2,53.8,64.3,78.6,12.5
claude-3.5-sonnet:beta,100.0,100.0,100.0,100.0,85.7,100.0,50.0,97.2,100.0,88.9,95.1,100.0,100.0,50.0,93.8,69.2,50.0,92.9,62.5
command-r-plus,90.6,0.0,100.0,88.3,14.3,0.0,50.0,80.3,57.1,66.7,85.2,0.0,100.0,50.0,79.2,46.2,57.1,61.9,12.5
dolphin-llama-3-70b,100.0,50.0,100.0,91.7,28.6,0.0,50.0,93.0,71.4,44.4,81.5,0.0,75.0,50.0,70.8,53.8,64.3,69.0,12.5
gemini-flash-1.5,90.6,0.0,0.0,86.7,71.4,100.0,33.3,93.0,85.7,88.9,88.9,0.0,100.0,50.0,81.2,38.5,50.0,81.0,0.0
gemini-pro,96.9,0.0,0.0,90.0,14.3,0.0,16.7,80.3,71.4,66.7,88.9,0.0,100.0,0.0,79.2,46.2,64.3,69.0,0.0
gemini-pro-1.5,96.9,0.0,0.0,90.0,42.9,100.0,33.3,87.3,42.9,77.8,87.6,0.0,100.0,50.0,79.2,46.2,85.7,85.7,12.5
gemma-2-27b-it,96.9,50.0,0.0,90.0,71.4,0.0,33.3,88.7,71.4,77.8,82.7,0.0,100.0,0.0,85.4,69.2,64.3,71.4,25.0
gemma-2-9b-it,96.9,50.0,0.0,88.3,14.3,0.0,33.3,83.1,42.9,66.7,77.8,0.0,50.0,0.0,79.2,61.5,57.1,61.9,12.5
gpt-3.5-turbo-0125,84.4,0.0,0.0,73.3,14.3,0.0,50.0,53.5,42.9,44.4,67.9,0.0,75.0,50.0,68.8,46.2,71.4,52.4,0.0
gpt-4-turbo,100.0,100.0,100.0,91.7,71.4,100.0,66.7,87.3,100.0,100.0,92.6,100.0,100.0,50.0,89.6,53.8,57.1,81.0,12.5
gpt-4o,81.2,100.0,100.0,80.0,71.4,100.0,50.0,81.7,85.7,88.9,84.0,0.0,100.0,50.0,79.2,38.5,64.3,61.9,12.5
gpt-4o-mini,93.8,0.0,0.0,93.3,42.9,0.0,50.0,88.7,71.4,66.7,82.7,0.0,75.0,50.0,81.2,69.2,50.0,71.4,12.5
llama-3-70b-instruct,96.9,0.0,0.0,90.0,14.3,0.0,33.3,87.3,71.4,66.7,79.0,0.0,75.0,0.0,68.8,46.2,71.4,76.2,0.0
llama-3-8b-instruct,65.6,0.0,0.0,66.7,0.0,0.0,16.7,57.8,28.6,11.1,42.0,0.0,0.0,0.0,54.2,15.4,28.6,57.1,0.0
llama-3.1-405b-instruct,100.0,100.0,100.0,96.7,71.4,0.0,83.3,91.6,100.0,77.8,91.4,100.0,75.0,0.0,87.5,61.5,50.0,81.0,12.5
llama-3.1-70b-instruct,96.9,50.0,0.0,93.3,57.1,0.0,50.0,94.4,71.4,88.9,87.6,100.0,75.0,50.0,77.1,46.2,71.4,78.6,12.5
llama-3.1-8b-instruct,71.9,0.0,0.0,71.7,0.0,0.0,16.7,60.6,42.9,22.2,61.7,0.0,25.0,0.0,66.7,7.7,42.9,61.9,0.0
llama-3.2-11b-vision-instruct,78.1,0.0,0.0,80.0,0.0,0.0,33.3,64.8,14.3,66.7,64.2,0.0,75.0,0.0,68.8,23.1,64.3,64.3,0.0
llama-3.2-1b-instruct,25.0,0.0,0.0,23.3,0.0,0.0,16.7,18.3,0.0,11.1,9.9,0.0,0.0,0.0,10.4,0.0,28.6,23.8,0.0
llama-3.2-3b-instruct,31.2,0.0,0.0,23.3,0.0,0.0,0.0,18.3,0.0,11.1,29.6,0.0,0.0,0.0,33.3,7.7,35.7,47.6,0.0
llama-3.2-90b-vision-instruct,96.9,100.0,100.0,93.3,42.9,0.0,33.3,95.8,57.1,88.9,88.9,100.0,75.0,50.0,81.2,53.8,71.4,71.4,12.5
maestrale-chat-v0.4-beta,65.6,0.0,0.0,66.7,14.3,0.0,0.0,62.0,0.0,33.3,60.5,0.0,25.0,0.0,62.5,23.1,35.7,71.4,0.0
mistral-7b-instruct:nitro,71.9,0.0,0.0,66.7,0.0,0.0,16.7,59.2,14.3,33.3,50.6,0.0,25.0,0.0,50.0,23.1,28.6,57.1,0.0
mistral-large,96.9,100.0,100.0,96.7,57.1,100.0,66.7,90.1,100.0,100.0,93.8,100.0,100.0,0.0,87.5,61.5,71.4,83.3,12.5
mistral-nemo,81.2,0.0,0.0,75.0,14.3,0.0,50.0,66.2,28.6,44.4,66.7,0.0,75.0,0.0,60.4,30.8,57.1,64.3,0.0
mixtral-8x22b-instruct,93.8,50.0,0.0,88.3,57.1,100.0,66.7,85.9,85.7,88.9,91.4,0.0,100.0,0.0,79.2,61.5,71.4,64.3,25.0
mixtral-8x7b-instruct,96.9,0.0,0.0,76.7,14.3,0.0,16.7,80.3,57.1,55.6,71.6,0.0,75.0,0.0,68.8,30.8,57.1,69.0,0.0
modello-italia-9b,25.0,0.0,0.0,31.7,0.0,0.0,0.0,29.6,0.0,22.2,27.2,0.0,25.0,0.0,35.4,0.0,7.1,33.3,0.0
nemotron-4-340b-instruct,87.5,0.0,100.0,76.7,71.4,0.0,16.7,74.6,28.6,55.6,81.5,100.0,100.0,50.0,75.0,53.8,50.0,73.8,12.5
o1-mini,93.8,100.0,0.0,91.7,57.1,0.0,83.3,78.9,100.0,66.7,86.4,0.0,100.0,0.0,85.4,69.2,78.6,71.4,12.5
o1-preview,100.0,100.0,100.0,96.7,85.7,100.0,83.3,95.8,100.0,88.9,96.3,100.0,100.0,50.0,95.8,61.5,71.4,78.6,12.5
phi-3-medium-128k-instruct,62.5,0.0,0.0,58.3,14.3,0.0,0.0,59.2,14.3,33.3,60.5,0.0,50.0,0.0,64.6,15.4,28.6,40.5,0.0
phi-3-mini-128k-instruct,34.4,0.0,0.0,30.0,0.0,0.0,0.0,33.8,14.3,22.2,42.0,0.0,25.0,0.0,35.4,7.7,35.7,54.8,0.0
qwen-2-72b-instruct,87.5,100.0,100.0,90.0,57.1,0.0,50.0,81.7,100.0,66.7,87.6,100.0,75.0,50.0,79.2,61.5,50.0,76.2,12.5
zefiro-7b-base-ITA,56.2,0.0,0.0,55.0,0.0,0.0,16.7,56.3,0.0,33.3,43.2,0.0,0.0,0.0,41.7,15.4,42.9,54.8,0.0