LLMArena commited on
Commit
6e35af2
·
verified ·
1 Parent(s): 73fff04

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -0
app.py CHANGED
@@ -50,6 +50,7 @@ def make_arena_leaderboard_md(arena_df, last_updated_time):
50
 
51
  leaderboard_md = f"""
52
  Total # of models: **{total_models}**.{space} Total # of votes: **{"{:,}".format(total_votes)}**.{space} Last updated: {last_updated_time}.
 
53
  ***Rank (UB)**: model rating (upper bound), determined as one plus the number of models that are statistically better than the target model.
54
  Model A is statistically better than Model B when the lower bound of Model A's rating is higher than the upper bound of Model B's rating (with a 95% confidence interval).
55
  See Figure 1 below for a visualization of the confidence intervals of model ratings.
 
50
 
51
  leaderboard_md = f"""
52
  Total # of models: **{total_models}**.{space} Total # of votes: **{"{:,}".format(total_votes)}**.{space} Last updated: {last_updated_time}.
53
+
54
  ***Rank (UB)**: model rating (upper bound), determined as one plus the number of models that are statistically better than the target model.
55
  Model A is statistically better than Model B when the lower bound of Model A's rating is higher than the upper bound of Model B's rating (with a 95% confidence interval).
56
  See Figure 1 below for a visualization of the confidence intervals of model ratings.