new runs LLAMA MODELS

src/macro_area.csv

@@ -22,6 +22,8 @@ gpt-4o-mini,80.6,86.0,81.8,85.7,55.2,70.8,0.0,57.9,83.3
 llama-3-70b-instruct,83.3,85.5,75.8,71.4,55.2,33.3,0.0,47.4,50.0
 llama-3-8b-instruct,48.2,53.6,63.6,14.3,34.5,29.2,0.0,31.6,50.0
 llama-3.1-405b-instruct,85.2,87.7,84.8,100.0,82.8,83.3,50.0,84.2,100.0
+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-nemo,64.8,71.0,57.6,28.6,44.8,33.3,0.0,47.4,83.3

src/question_format.csv

@@ -22,6 +22,8 @@ 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
 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
 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-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