Hugging Face's logo

Spaces:
speakleash
/
polish_eq-bench
Running

App Files Community
1
djstrong commited on
Commit
492a075
•
1 Parent(s): 23d7973

eq bench

Browse files
Files changed (1) hide show
  1. benchmark_results.csv +1 -0
benchmark_results.csv CHANGED
@@ -147,3 +147,4 @@ Qwen/Qwen1.5-72B,2024-06-20 17:50:17,,Qwen/Qwen1.5-72B,,,53.96,eq-bench_v2_pl,16
147
  Qwen/Qwen1.5-72B-Chat,2024-06-20 18:06:58,,Qwen/Qwen1.5-72B-Chat,,,68.03,eq-bench_v2_pl,171.0,1,transformers, ,,
148
  Qwen/Qwen2-72B,2024-06-20 18:36:22,,Qwen/Qwen2-72B,,,69.75,eq-bench_v2_pl,169.0,1,transformers, ,,
149
  Qwen/Qwen2-72B-Instruct,2024-06-20 18:55:02,,Qwen/Qwen2-72B-Instruct,,,72.07,eq-bench_v2_pl,169.0,1,transformers, ,,
 
 
147
  Qwen/Qwen1.5-72B-Chat,2024-06-20 18:06:58,,Qwen/Qwen1.5-72B-Chat,,,68.03,eq-bench_v2_pl,171.0,1,transformers, ,,
148
  Qwen/Qwen2-72B,2024-06-20 18:36:22,,Qwen/Qwen2-72B,,,69.75,eq-bench_v2_pl,169.0,1,transformers, ,,
149
  Qwen/Qwen2-72B-Instruct,2024-06-20 18:55:02,,Qwen/Qwen2-72B-Instruct,,,72.07,eq-bench_v2_pl,169.0,1,transformers, ,,
150
+ mistralai/Mixtral-8x22B-v0.1,2024-06-21 20:20:37,,mistralai/Mixtral-8x22B-v0.1,,,FAILED,eq-bench_pl,FAILED,1,transformers, ,,34.0 questions were parseable (min is 83%)