Update app.py

app.py

@@ -26,7 +26,7 @@ def make_leaderboard_md(elo_results):
 - [MT-Bench](https://arxiv.org/abs/2306.05685) - a set of challenging multi-turn questions. We use GPT-4 to grade the model responses.
 - [MMLU](https://arxiv.org/abs/2009.03300) (5-shot) - a test to measure a model's multitask accuracy on 57 tasks.
 
-💻 Code: The Arena Elo ratings are computed by this [notebook]({notebook_url}). The MT-bench scores (single-answer grading on a scale of 10) are computed by [fastchat.llm_judge](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge). The MMLU scores are mostly computed by [InstructEval](https://github.com/declare-lab/instruct-eval). Higher values are better for all benchmarks. Empty cells mean not available. Last updated: Dec 15, 2023.
+💻 Code: The Arena Elo ratings are computed by this [notebook]({notebook_url}). The MT-bench scores (single-answer grading on a scale of 10) are computed by [fastchat.llm_judge](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge). The MMLU scores are mostly computed by [InstructEval](https://github.com/declare-lab/instruct-eval). Higher values are better for all benchmarks. Empty cells mean not available. Last updated: Dec 20, 2023.
 """
     return leaderboard_md
 
@@ -105,7 +105,7 @@ def load_leaderboard_table_csv(filename, add_hyperlink=True):
         for j in range(len(heads)):
             item = {}
             for h, v in zip(heads, row):
-                if h == "Arena Elo rating":
+                if h == "Arena Elo":
                     if v != "-":
                         v = int(ast.literal_eval(v))
                     else: