update data and update links

app.py

@@ -1026,7 +1026,7 @@ with gr.Blocks() as demo:
     with gr.Tabs():
         with gr.TabItem("Summary Leaderboard"):
             gr.Markdown(
-                "**This live leaderboard evaluates the LLM's ability to call functions (aka tools) accurately. This leaderboard consists of real-world data and will be updated periodically. For more information on the evaluation dataset and methodology, please refer to our [blog](https://gorilla.cs.berkeley.edu/blogs/10_checker_manual.html) and [code](https://github.com/ShishirPatil/gorilla).**"
+                "**This live leaderboard evaluates the LLM's ability to call functions (aka tools) accurately. This leaderboard consists of real-world data and will be updated periodically. For more information on the evaluation dataset and methodology, please refer to our [blog](https://gorilla.cs.berkeley.edu/blogs/8_berkeley_function_calling_leaderboard.html) and [code](https://github.com/ShishirPatil/gorilla).**"
             )
             gr.Markdown(
                 """**AST means evaluation through Abstract Syntax Tree and Exec means evaluation through execution.**
@@ -1043,7 +1043,7 @@ with gr.Blocks() as demo:
             leaderboard_data = gr.Dataframe(value=get_summary(), wrap=True)
         with gr.TabItem("Full Leaderboard"):
             gr.Markdown(
-                "**This live leaderboard evaluates the LLM's ability to call functions (aka tools) accurately. This leaderboard consists of real-world data and will be updated periodically. For more information on the evaluation dataset and methodology, please refer to our [blog](https://gorilla.cs.berkeley.edu/blogs/10_checker_manual.html) and [code](https://github.com/ShishirPatil/gorilla).**"
+                "**This live leaderboard evaluates the LLM's ability to call functions (aka tools) accurately. This leaderboard consists of real-world data and will be updated periodically. For more information on the evaluation dataset and methodology, please refer to our [blog](https://gorilla.cs.berkeley.edu/blogs/8_berkeley_function_calling_leaderboard.html) and [code](https://github.com/ShishirPatil/gorilla).**"
             )
             gr.Markdown(
                 """**AST means evaluation through Abstract Syntax Tree and Exec means evaluation through execution.**

data.csv

@@ -1,4 +1,4 @@
-Rank,Overall Acc,Model,Model Link,Organization,License,AST Summary,Exec Summary,Simple Function AST,Python Simple Function AST,Java Simple Function AST,JavaScript Simple Function AST,Multiple Functions AST,Parallel Functions AST,Parallel Multiple AST,Simple Function Exec,Python Simple Function Exec,REST Simple Function Exec,Multiple Functions Exec,Parallel Functions Exec,Parallel Multiple Exec,Relevance Detection,Cost ($ Per 1k Function Calls),Latency Mean (s),Latency Standard Deviation (s),,
+Rank,Overall Acc,Model,Model Link,Organization,License,AST Summary,Exec Summary,Simple Function AST,Python Simple Function AST,Java Simple Function AST,JavaScript Simple Function AST,Multiple Functions AST,Parallel Functions AST,Parallel Multiple AST,Simple Function Exec,Python Simple Function Exec,REST Simple Function Exec,Multiple Functions Exec,Parallel Functions Exec,Parallel Multiple Exec,Relevance Detection,Cost ($ Per 1k Function Calls),Latency Mean (s),Latency Standard Deviation (s)
 1,79.35%,Claude-3-Opus-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,79.02%,68.13%,83.09%,89.25%,64.00%,72.00%,90.50%,80.00%,62.50%,83.53%,84.00%,82.86%,74.00%,70.00%,45.00%,80.83%,10.81,5.67,1.43
 2,78.71%,GPT-4-0125-Preview (Prompt),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,81.16%,67.36%,83.64%,89.00%,65.00%,78.00%,90.00%,86.50%,64.50%,82.94%,83.00%,82.86%,76.00%,68.00%,42.50%,69.17%,5.22,2.1,1.4
 3,78.35%,Gorilla-OpenFunctions-v2 (FC),https://gorilla.cs.berkeley.edu/blogs/7_open_functions_v2.html,Gorilla LLM,Apache 2.0,81.94%,69.64%,83.27%,93.00%,53.00%,66.00%,93.00%,85.50%,66.00%,87.06%,83.00%,92.86%,76.00%,68.00%,47.50%,60.83%,1.53,2.38,2.05
@@ -6,7 +6,7 @@ Rank,Overall Acc,Model,Model Link,Organization,License,AST Summary,Exec Summary,
 5,77.71%,GPT-4-1106-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,78.86%,67.10%,77.45%,87.25%,48.00%,58.00%,88.00%,88.00%,62.00%,79.41%,81.00%,77.14%,74.00%,70.00%,45.00%,80.83%,4.95,6.45,6.45
 6,73.82%,Claude-3-Sonnet-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,78.86%,66.07%,79.45%,88.25%,52.00%,64.00%,85.50%,85.00%,65.50%,75.29%,74.00%,77.14%,74.00%,70.00%,45.00%,53.33%,2.13,2.38,0.66
 7,72.24%,Mistral-Medium-2312 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,70.31%,56.79%,74.73%,82.75%,54.00%,52.00%,73.50%,79.50%,53.50%,67.65%,77.00%,54.29%,68.00%,64.00%,27.50%,88.33%,1.75,3.41,4.65
-8,70.71%,Functionary-Small (FC),https://huggingface.co/meetkai/functionary-small-v2.2,MeetKai,MIT,72.72%,60.75%,72.36%,83.25%,41.00%,48.00%,86.50%,76.50%,55.50%,60.00%,81.00%,30.00%,72.00%,66.00%,45.00%,74.17%,1.94,3.02,3.2
+8,70.71%,Functionary-Small (FC),https://huggingface.co/meetkai/functionary-small-v2.2,MeetKai,MIT,72.72%,60.75%,72.36%,83.25%,41.00%,48.00%,86.50%,76.50%,55.50%,60.00%,81.00%,30.00%,72.00%,66.00%,45.00%,74.17%,N/A,3.02,3.2
 9,69.18%,Claude-instant-1.2 (Prompt),https://www.anthropic.com/news/releasing-claude-instant-1-2,Anthropic,Proprietary,71.17%,61.37%,76.18%,83.75%,53.00%,62.00%,84.00%,78.50%,46.00%,76.47%,81.00%,70.00%,66.00%,58.00%,45.00%,54.17%,0.95,1.75,1
 10,68.24%,Claude-3-Opus-20240229 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,69.17%,61.85%,70.18%,81.25%,38.00%,46.00%,74.50%,75.00%,57.00%,75.88%,81.00%,68.57%,66.00%,68.00%,37.50%,62.50%,26.58,14.82,6
 11,66.00%,Mistral-Small-2402 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,73.30%,29.07%,76.18%,82.75%,57.00%,62.00%,83.50%,81.00%,52.50%,25.29%,1.00%,60.00%,6.00%,60.00%,25.00%,76.25%,1.04,1.62,1.75
@@ -19,8 +19,8 @@ Rank,Overall Acc,Model,Model Link,Organization,License,AST Summary,Exec Summary,
 18,56.65%,GPT-3.5-Turbo-0125 (FC),https://platform.openai.com/docs/models/gpt-3-5-turbo,OpenAI,Proprietary,66.31%,66.38%,56.73%,57.75%,51.00%,60.00%,65.50%,86.00%,57.00%,83.53%,78.00%,91.43%,70.00%,72.00%,40.00%,2.08%,0.42,1.53,1.25
 19,55.82%,Gemini-1.0-Pro (FC),https://deepmind.google/technologies/gemini/#introduction,Google,Proprietary,40.92%,38.68%,76.18%,87.50%,43.00%,52.00%,87.50%,0.00%,0.00%,78.24%,83.00%,71.43%,74.00%,0.00%,2.50%,76.67%,0.18,1.05,0.23
 20,54.82%,Mistral-small-2402 (FC Any),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,58.92%,46.38%,78.18%,86.00%,56.00%,60.00%,90.00%,36.50%,31.00%,80.00%,84.00%,74.29%,76.00%,12.00%,17.50%,0.00%,0.95,1.14,1.15
-21,50.18%,Nexusflow-Raven-v2 (FC),https://huggingface.co/Nexusflow/NexusRaven-V2-13B,Nexusflow,Apache 2.0,55.36%,56.95%,65.45%,70.50%,49.00%,58.00%,81.00%,35.00%,40.00%,55.29%,78.00%,22.86%,72.00%,58.00%,42.50%,2.08%,1.22,1.9,1.57
-22,49.88%,FireFunction-v1 (FC),https://huggingface.co/fireworks-ai/firefunction-v1,Fireworks,Apache 2.0,37.56%,32.19%,66.73%,85.75%,13.00%,22.00%,83.50%,0.00%,0.00%,61.76%,73.00%,45.71%,62.00%,0.00%,5.00%,73.33%,0.59,0.92,0.8
+21,50.18%,Nexusflow-Raven-v2 (FC),https://huggingface.co/Nexusflow/NexusRaven-V2-13B,Nexusflow,Apache 2.0,55.36%,56.95%,65.45%,70.50%,49.00%,58.00%,81.00%,35.00%,40.00%,55.29%,78.00%,22.86%,72.00%,58.00%,42.50%,2.08%,N/A,1.9,1.57
+22,49.88%,FireFunction-v1 (FC),https://huggingface.co/fireworks-ai/firefunction-v1,Fireworks,Apache 2.0,37.56%,32.19%,66.73%,85.75%,13.00%,22.00%,83.50%,0.00%,0.00%,61.76%,73.00%,45.71%,62.00%,0.00%,5.00%,73.33%,N/A,0.92,0.8
 23,47.94%,GPT-4-0613 (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,36.57%,25.10%,59.27%,80.50%,3.00%,2.00%,87.00%,0.00%,0.00%,39.41%,55.00%,17.14%,56.00%,0.00%,5.00%,90.83%,10.27,3.64,3.99
 24,46.35%,Mistral-tiny-2312 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,41.98%,27.32%,48.91%,60.25%,28.00%,0.00%,48.50%,44.50%,26.00%,21.76%,36.00%,1.43%,28.00%,42.00%,17.50%,84.17%,0.13,1.14,1.19
 25,39.29%,Gemma-7b-it (Prompt),https://blog.google/technology/developers/gemma-open-models/,Google,gemma-terms-of-use,38.10%,27.93%,40.91%,46.25%,28.00%,24.00%,49.00%,29.50%,33.00%,24.71%,38.00%,5.71%,32.00%,30.00%,25.00%,57.08%,0.03,0.09,N/A