adadtur commited on
Commit
d3f7085
·
verified ·
1 Parent(s): cee44e8

Update results.csv

Browse files
Files changed (1) hide show
  1. results.csv +2 -2
results.csv CHANGED
@@ -1,6 +1,6 @@
1
  Model,Safe Completion Rate,Harmful Completion Rate,Refusal Rate,Normalized Safety Score,License,Bias Completion Rate,Cybercrime Completion Rate,Harassment Completion Rate,Misinformation Completion Rate,Illegal Activity Completion Rate
2
  GPT-4o,34.4,22.8,30.2,31.7,Proprietary,14.0,16.0,16.0,28.0,40.0
3
  GPT-4o-Mini,18.4,14.0,36.5,35.7,Proprietary,6.0,8.0,14.0,24.0,18.0
4
- Claude-3.5-Sonnet,21.2,7.6,57.7,55.0,Proprietary,4.0,6.0,5.0,12.0,12.0
5
- Llama-3.2-90B,8.4,11.2,14.0,34.0,Llama License,22.0,8.0,10.0,14.0,2.0
6
  Qwen-2-VL-72B,24.4,26.0,0.8,21.5,Qwen License,34.0,18.0,18.0,30.0,30.0
 
1
  Model,Safe Completion Rate,Harmful Completion Rate,Refusal Rate,Normalized Safety Score,License,Bias Completion Rate,Cybercrime Completion Rate,Harassment Completion Rate,Misinformation Completion Rate,Illegal Activity Completion Rate
2
  GPT-4o,34.4,22.8,30.2,31.7,Proprietary,14.0,16.0,16.0,28.0,40.0
3
  GPT-4o-Mini,18.4,14.0,36.5,35.7,Proprietary,6.0,8.0,14.0,24.0,18.0
4
+ Claude-3.5-Sonnet-202406,21.2,7.6,57.7,55.0,Proprietary,4.0,6.0,5.0,12.0,12.0
5
+ llama-3.2-90b-Vision-Instruct,8.4,11.2,14.0,34.0,Llama License,22.0,8.0,10.0,14.0,2.0
6
  Qwen-2-VL-72B,24.4,26.0,0.8,21.5,Qwen License,34.0,18.0,18.0,30.0,30.0