new models

src/macro_area.csv

@@ -3,6 +3,8 @@ MacroAspetto,Localizzare e individuare informazioni all’interno del testo,"Ric
 Model,,,,,,,,,
 LLaMAntino-3-ANITA-8B-Inst-DPO-ITA,60.2,63.1,78.8,28.6,37.9,16.7,0.0,26.3,50.0
 Llama-3-8b-Ita,66.7,64.2,81.8,42.9,48.3,25.0,0.0,26.3,50.0
+Llama-3-COT-ITA,38.0,40.2,33.3,28.6,24.1,20.8,0.0,15.8,50.0
+Llama-3.1-8b-Ita,69.4,69.8,69.7,57.1,34.5,29.2,0.0,21.0,83.3
 Minerva-3B-base-v1.0,4.6,3.9,9.1,28.6,3.4,4.2,0.0,5.3,0.0
 Minerva_3B_Ties_1.0,37.0,20.7,36.4,14.3,44.8,41.7,0.0,31.6,66.7
 claude-3-haiku,78.7,86.0,75.8,71.4,65.5,62.5,0.0,57.9,83.3
@@ -27,6 +29,7 @@ llama-3.1-70b-instruct,83.3,87.2,81.8,100.0,79.3,58.3,25.0,79.0,83.3
 llama-3.1-8b-instruct,64.8,62.0,66.7,57.1,37.9,16.7,0.0,26.3,66.7
 maestrale-chat-v0.4-beta,62.0,61.4,60.6,42.9,44.8,33.3,0.0,15.8,50.0
 mistral-7b-instruct:nitro,51.8,59.2,51.5,28.6,37.9,29.2,0.0,31.6,33.3
+mistral-large,87.0,89.9,81.8,85.7,93.1,83.3,25.0,84.2,100.0
 mistral-nemo,64.8,71.0,57.6,28.6,44.8,33.3,0.0,47.4,83.3
 mixtral-8x22b-instruct,84.3,85.5,81.8,71.4,58.6,83.3,0.0,68.4,83.3
 mixtral-8x7b-instruct,74.1,77.1,69.7,42.9,37.9,50.0,0.0,52.6,50.0

src/question_format.csv

@@ -3,6 +3,8 @@ Type,MC,MCC,CL,MC,MCC,RB,RU,MC,MCC,RU,MC,MCC,RU,CL,MC,MCC,RU,MC,MCC
 Model,,,,,,,,,,,,,,,,,,,
 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
@@ -27,6 +29,7 @@ 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.
 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
 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