Miiche commited on
Commit
11ce63b
·
verified ·
1 Parent(s): 948780b

eval results sync

Browse files
eval_results/agopd-v3-s90/hallusionbench_scores.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "benchmark": "hallusionbench",
3
+ "n_shards": 4,
4
+ "correct": 655,
5
+ "total": 951,
6
+ "accuracy": 0.6887486855941115,
7
+ "final_score": 0.6887486855941115
8
+ }