dror44 commited on
Commit
38d5bbd
·
1 Parent(s): e7e1116
benchmarks/safety/moderation-api-1680-samples-judges-metrics.csv CHANGED
@@ -1,5 +1,5 @@
1
  dataset,judge_id,judge_name,f1,bacc,avg_latency,total_latency,count,correct
2
- moderation-api-1680,qualifire-eval,Qualifire,0.8334630350194552,0.9054116292458262,0.03659970967542557,1622.8751225471497,1680,1406
3
  moderation-api-1680,meta-llama-3.1-70b-instruct-turbo,Meta Llama 3.1 70B Instruct,0.7603930461073318,0.8531306453854248,1.7941580413352876,3014.185509443283,1680,1363
4
  moderation-api-1680,meta-llama-3.1-405b-instruct-turbo,Meta Llama 3.1 405B Instruct,0.7858267716535433,0.8704563952911282,2.1023602211759203,3531.9651715755463,1680,1408
5
  moderation-api-1680,meta-llama-4-scout-17B-16E-instruct,Meta Llama 4 Scout 17B 16E Instruct,0.7520723436322532,0.8458449963273975,13.005298352383432,21848.901232004166,1680,1351
 
1
  dataset,judge_id,judge_name,f1,bacc,avg_latency,total_latency,count,correct
2
+ moderation-api-1680,qualifire-eval,Qualifire,0.8334630350194552,0.9054116292458262,0.03659970967542557,59.9751225471497,1680,1406
3
  moderation-api-1680,meta-llama-3.1-70b-instruct-turbo,Meta Llama 3.1 70B Instruct,0.7603930461073318,0.8531306453854248,1.7941580413352876,3014.185509443283,1680,1363
4
  moderation-api-1680,meta-llama-3.1-405b-instruct-turbo,Meta Llama 3.1 405B Instruct,0.7858267716535433,0.8704563952911282,2.1023602211759203,3531.9651715755463,1680,1408
5
  moderation-api-1680,meta-llama-4-scout-17B-16E-instruct,Meta Llama 4 Scout 17B 16E Instruct,0.7520723436322532,0.8458449963273975,13.005298352383432,21848.901232004166,1680,1351