lfqian commited on
Commit
92d7e60
·
verified ·
1 Parent(s): 6903ed3

Upload model_performance.csv

Browse files
Files changed (1) hide show
  1. model_performance.csv +19 -0
model_performance.csv ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models,finqa,dm-simplong,xbrl-math
2
+ 4o,72.49,60.0,72.22
3
+ o1,49.07,56.0,74.44
4
+ o3-mini,60.87,59.0,76.67
5
+ v3,73.2,53.0,76.67
6
+ r1,65.13,53.0,86.67
7
+ deepseek-70b,66.73,53.0,86.67
8
+ llama3-70B-instruct,58.92,41.0,56.67
9
+ llama31-70B-instruct,63.18,48.0,63.33
10
+ llama33-70B-instruct,68.15,54.0,70.0
11
+ deepseek-32b,65.48,55.0,84.44
12
+ deepseek-14b,63.27,44.0,84.44
13
+ deepseek-8b,45.96,33.0,81.11
14
+ llama3 8b-instruct,41.97,29.0,48.89
15
+ llama31 8b-instruct,54.13,34.0,62.22
16
+ Qwen2.5-32B-Instruct,,,
17
+ Qwen2.5-72B-Instruct,73.38,59.0,67.78
18
+ Qwen2.5-72B-Instruct-math,69.74,42.0,83.33
19
+ Fino1-8B,60.87,40.0,82.22