Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Leaderboard Update, in sync with BFCL April 9th Release #341

Merged
merged 5 commits into from
Apr 11, 2024
Merged

Leaderboard Update, in sync with BFCL April 9th Release #341

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
0ecd161
update data.csv. April 9
HuanzhiMao Apr 11, 2024
6713be1
update treemap
HuanzhiMao Apr 11, 2024
59e7fbf
update data.csv
HuanzhiMao Apr 11, 2024
93ddad7
Merge branch 'gh-pages' into gh-pages
HuanzhiMao Apr 11, 2024
92dabb2
update treemap
HuanzhiMao Apr 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 29 additions & 29 deletions data.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,30 +1,30 @@
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)
1,80.47%,Claude-3-Opus-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,80.30%,69.57%,84.18%,90.25%,65.00%,74.00%,92.00%,81.00%,64.00%,85.29%,87.00%,82.86%,76.00%,72.00%,45.00%,80.83%,10.81,5.67,1.43
2,79.94%,GPT-4-0125-Preview (Prompt),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,82.48%,69.30%,84.91%,90.00%,67.00%,80.00%,90.50%,87.50%,67.00%,84.71%,86.00%,82.86%,78.00%,72.00%,42.50%,69.17%,5.22,2.1,1.4
3,78.88%,Gorilla-OpenFunctions-v2 (FC),https://gorilla.cs.berkeley.edu/blogs/7_open_functions_v2.html,Gorilla LLM,Apache 2.0,82.41%,70.93%,83.64%,93.50%,53.00%,66.00%,93.50%,85.50%,67.00%,88.24%,85.00%,92.86%,78.00%,70.00%,47.50%,60.83%,1.53,2.38,2.05
4,78.76%,GPT-4-0125-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,81.58%,65.17%,79.82%,89.75%,56.00%,48.00%,91.50%,89.00%,66.00%,71.18%,84.00%,52.86%,70.00%,72.00%,47.50%,81.67%,4.76,4.37,5.31
5,78.53%,GPT-4-1106-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,79.56%,68.40%,78.73%,88.50%,49.00%,60.00%,88.50%,88.50%,62.50%,80.59%,83.00%,77.14%,76.00%,72.00%,45.00%,80.83%,4.95,6.45,6.45
6,74.71%,Claude-3-Sonnet-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,80.00%,67.37%,80.00%,89.00%,52.00%,64.00%,86.00%,87.00%,67.00%,76.47%,76.00%,77.14%,76.00%,72.00%,45.00%,53.33%,2.13,2.38,0.66
7,74.29%,Functionary-Medium-v2.4 (FC),https://huggingface.co/meetkai/functionary-medium-v2.4,MeetKai,MIT,77.14%,61.96%,78.55%,85.75%,57.00%,64.00%,88.50%,80.00%,61.50%,58.82%,80.00%,28.57%,68.00%,76.00%,45.00%,75.42%,1.64,2.56,2.51
8,73.06%,Functionary-Small-v2.4 (FC),https://huggingface.co/meetkai/functionary-small-v2.4,MeetKai,MIT,75.38%,64.14%,78.00%,86.00%,54.00%,62.00%,83.00%,80.50%,60.00%,67.06%,81.00%,47.14%,66.00%,76.00%,47.50%,67.50%,1.76,2.74,2.55
9,72.88%,Mistral-Medium-2312 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,71.10%,58.08%,74.91%,83.00%,54.00%,52.00%,74.00%,80.00%,55.50%,68.82%,79.00%,54.29%,70.00%,66.00%,27.50%,88.33%,1.75,3.41,4.65
10,70.29%,Claude-instant-1.2 (Prompt),https://www.anthropic.com/news/releasing-claude-instant-1-2,Anthropic,Proprietary,72.27%,63.46%,77.09%,84.50%,55.00%,62.00%,85.00%,79.50%,47.50%,78.82%,85.00%,70.00%,68.00%,62.00%,45.00%,54.17%,0.95,1.75,1.0
11,69.53%,Claude-3-Opus-20240229 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,70.82%,63.76%,71.27%,82.00%,40.00%,48.00%,75.50%,76.50%,60.00%,77.06%,83.00%,68.57%,68.00%,70.00%,40.00%,62.50%,26.58,14.82,6.0
12,66.71%,Mistral-Small-2402 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,74.23%,30.07%,76.91%,83.50%,58.00%,62.00%,84.00%,81.00%,55.00%,25.29%,1.00%,60.00%,8.00%,62.00%,25.00%,76.25%,1.04,1.62,1.75
13,65.00%,Claude-3-Sonnet-20240229 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,67.70%,60.55%,69.82%,79.25%,38.00%,58.00%,71.50%,73.50%,56.00%,64.71%,85.00%,35.71%,70.00%,70.00%,37.50%,51.67%,5.08,6.7,3.07
14,64.24%,Claude-2.1 (Prompt),https://www.anthropic.com/news/claude-2-1,Anthropic,Proprietary,60.10%,46.48%,74.91%,80.75%,59.00%,60.00%,73.50%,56.00%,36.00%,49.41%,63.00%,30.00%,68.00%,36.00%,32.50%,83.33%,6.62,3.2,1.42
15,63.29%,Claude-3-Haiku-20240307 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,72.86%,59.57%,75.45%,85.00%,51.00%,48.00%,77.00%,77.00%,62.00%,51.76%,84.00%,5.71%,74.00%,70.00%,42.50%,21.67%,0.44,3.81,2.32
16,63.12%,Mistral-large-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,58.19%,48.62%,65.27%,88.50%,3.00%,4.00%,89.00%,23.00%,55.50%,70.00%,77.00%,60.00%,74.00%,8.00%,42.50%,84.17%,4.74,2.91,2.73
17,61.59%,DBRX-Instruct (Prompt),https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm,Databricks,Databricks Open Model,63.55%,60.54%,62.18%,73.00%,26.00%,48.00%,73.50%,73.00%,45.50%,61.18%,79.00%,35.71%,74.00%,62.00%,45.00%,54.58%,1.24,0.62,0.41
18,58.35%,Mistral-large-2402 (FC Any),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,64.61%,52.17%,79.45%,87.50%,58.00%,58.00%,90.50%,32.50%,56.00%,81.18%,85.00%,75.71%,76.00%,4.00%,47.50%,0.00%,3.86,1.99,2.53
19,57.65%,GPT-3.5-Turbo-0125 (FC),https://platform.openai.com/docs/models/gpt-3-5-turbo,OpenAI,Proprietary,67.41%,68.30%,57.64%,58.75%,52.00%,60.00%,67.00%,87.50%,57.50%,84.71%,80.00%,91.43%,72.00%,74.00%,42.50%,2.08%,0.42,1.53,1.25
20,56.35%,Gemini-1.0-Pro (FC),https://deepmind.google/technologies/gemini/#introduction,Google,Proprietary,41.48%,39.33%,76.91%,88.25%,43.00%,54.00%,89.00%,0.00%,0.00%,78.82%,84.00%,71.43%,76.00%,0.00%,2.50%,76.67%,0.18,1.05,0.23
21,55.76%,Mistral-small-2402 (FC Any),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,60.07%,47.17%,79.27%,87.25%,57.00%,60.00%,91.50%,37.00%,32.50%,81.18%,86.00%,74.29%,78.00%,12.00%,17.50%,0.00%,0.95,1.14,1.15
22,51.53%,Nexusflow-Raven-v2 (FC),https://huggingface.co/Nexusflow/NexusRaven-V2-13B,Nexusflow,Apache 2.0,56.91%,57.74%,67.64%,73.25%,49.00%,60.00%,83.00%,35.00%,42.00%,56.47%,80.00%,22.86%,74.00%,58.00%,42.50%,2.08%,N/A,1.9,1.57
23,50.29%,FireFunction-v1 (FC),https://huggingface.co/fireworks-ai/firefunction-v1,Fireworks,Apache 2.0,37.90%,32.99%,67.09%,86.00%,14.00%,22.00%,84.50%,0.00%,0.00%,62.94%,75.00%,45.71%,64.00%,0.00%,5.00%,73.33%,N/A,0.92,0.8
24,48.53%,GPT-4-0613 (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,37.05%,25.90%,60.18%,81.75%,3.00%,2.00%,88.00%,0.00%,0.00%,40.59%,57.00%,17.14%,58.00%,0.00%,5.00%,90.83%,10.27,3.64,3.99
25,47.29%,Mistral-tiny-2312 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,43.12%,27.76%,50.00%,61.75%,28.00%,0.00%,49.00%,46.00%,27.50%,23.53%,39.00%,1.43%,28.00%,42.00%,17.50%,84.17%,0.13,1.14,1.19
26,39.59%,Gemma-7b-it (Prompt),https://blog.google/technology/developers/gemma-open-models/,Google,gemma-terms-of-use,38.32%,28.57%,41.27%,46.50%,29.00%,24.00%,49.00%,29.50%,33.50%,25.29%,39.00%,5.71%,34.00%,30.00%,25.00%,57.08%,0.03,0.09,N/A
27,37.47%,Deepseek-v1.5 (Prompt),https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5,Deepseek,Deepseek License,33.73%,30.85%,36.91%,45.75%,7.00%,26.00%,41.50%,33.00%,23.50%,35.88%,41.00%,28.57%,40.00%,30.00%,17.50%,56.25%,0.45,1.2,N/A
28,30.00%,Glaive-v1 (FC),https://huggingface.co/glaiveai/glaive-function-calling-v1,Glaive,cc-by-sa-4.0,29.02%,0.00%,53.09%,71.25%,3.00%,8.00%,63.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,0.00%,38.33%,0.02,0.06,N/A
29,18.12%,Mistral-small-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,2.86%,7.79%,1.45%,2.00%,0.00%,0.00%,3.50%,4.00%,2.50%,21.18%,19.00%,24.29%,10.00%,0.00%,0.00%,99.58%,1.99,2.82,1.43
1,83.82%,GPT-4-0125-Preview (Prompt),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,88.75%,70.07%,88.00%,94.25%,67.00%,80.00%,94.50%,90.50%,82.00%,85.29%,86.00%,84.29%,78.00%,72.00%,45.00%,70.42%,5.21,1.99,1.27
2,83.53%,Claude-3-Opus-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,86.09%,69.43%,86.36%,93.25%,66.00%,72.00%,93.50%,86.00%,78.50%,84.71%,87.00%,81.43%,76.00%,72.00%,45.00%,80.42%,10.8,5.05,1.78
3,81.24%,GPT-4-1106-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,84.75%,67.29%,82.00%,90.25%,61.00%,58.00%,91.00%,91.50%,74.50%,77.65%,85.00%,67.14%,72.00%,72.00%,47.50%,80.42%,5.03,6.34,6.04
4,81.12%,Gorilla-OpenFunctions-v2 (FC),https://gorilla.cs.berkeley.edu/blogs/7_open_functions_v2.html,Gorilla LLM,Apache 2.0,86.16%,70.05%,87.64%,94.25%,67.00%,76.00%,94.50%,87.50%,75.00%,84.71%,87.00%,81.43%,78.00%,70.00%,47.50%,60.83%,1.7,2.65,2.33
5,79.94%,GPT-4-0125-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,83.75%,65.25%,80.00%,90.25%,53.00%,52.00%,92.50%,90.00%,72.50%,70.00%,84.00%,50.00%,74.00%,72.00%,45.00%,82.92%,4.82,5.03,5.88
6,78.94%,Mistral-Medium-2312 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,81.44%,61.16%,79.27%,88.50%,54.00%,56.00%,92.50%,84.00%,70.00%,67.65%,86.00%,41.43%,72.00%,70.00%,35.00%,88.75%,1.75,2.77,2.27
7,77.29%,Claude-3-Sonnet-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,85.20%,69.35%,81.82%,90.25%,53.00%,72.00%,88.50%,88.00%,82.50%,75.88%,75.00%,77.14%,78.00%,76.00%,47.50%,50.42%,2.12,2.11,1.15
8,76.88%,Functionary-Medium-v2.4 (FC),https://huggingface.co/meetkai/functionary-medium-v2.4,MeetKai,MIT,82.36%,62.38%,79.45%,88.00%,55.00%,60.00%,90.00%,87.50%,72.50%,60.00%,80.00%,31.43%,66.00%,76.00%,47.50%,74.17%,1.64,2.55,2.6
9,75.94%,Functionary-Small-v2.4 (FC),https://huggingface.co/meetkai/functionary-small-v2.4,MeetKai,MIT,80.00%,64.73%,80.00%,88.75%,56.00%,58.00%,89.00%,82.00%,69.00%,69.41%,81.00%,52.86%,68.00%,74.00%,47.50%,67.92%,1.76,2.74,2.47
10,72.65%,Claude-instant-1.2 (Prompt),https://www.anthropic.com/news/releasing-claude-instant-1-2,Anthropic,Proprietary,76.63%,63.20%,80.00%,87.25%,56.00%,70.00%,86.00%,83.00%,57.50%,75.29%,84.00%,62.86%,72.00%,58.00%,47.50%,54.17%,0.95,1.35,0.62
11,70.76%,Claude-3-Opus-20240229 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,73.43%,62.02%,72.73%,84.25%,39.00%,48.00%,80.00%,75.00%,66.00%,70.59%,80.00%,57.14%,70.00%,70.00%,37.50%,65.00%,26.31,13.56,5.21
12,66.53%,Claude-3-Sonnet-20240229 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,71.38%,62.10%,70.00%,79.50%,39.00%,56.00%,73.50%,76.50%,65.50%,59.41%,85.00%,22.86%,72.00%,72.00%,45.00%,51.67%,5.08,6.44,2.41
13,65.35%,Claude-3-Haiku-20240307 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,76.32%,59.07%,77.27%,86.75%,51.00%,54.00%,79.50%,78.50%,70.00%,51.76%,82.00%,8.57%,72.00%,70.00%,42.50%,22.50%,0.45,3.45,1.58
14,65.12%,Claude-2.1 (Prompt),https://www.anthropic.com/news/claude-2-1,Anthropic,Proprietary,62.59%,46.39%,74.36%,80.75%,54.00%,64.00%,75.50%,55.50%,45.00%,47.06%,63.00%,24.29%,66.00%,40.00%,32.50%,83.33%,6.64,3.72,2.02
15,64.59%,Mistral-large-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,62.09%,46.32%,66.36%,88.75%,5.00%,10.00%,94.00%,25.50%,62.50%,65.29%,76.00%,50.00%,76.00%,4.00%,40.00%,84.17%,4.94,2.84,2.57
16,64.24%,DBRX-Instruct (Prompt),https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm,Databricks,Databricks Open Model,65.31%,63.22%,66.73%,79.50%,30.00%,38.00%,72.00%,72.00%,50.50%,65.88%,76.00%,51.43%,70.00%,72.00%,45.00%,56.25%,1.25,0.63,0.45
17,61.12%,Mistral-large-2402 (FC Any),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,68.98%,50.99%,82.91%,91.50%,62.00%,56.00%,93.00%,31.50%,68.50%,82.94%,84.00%,81.43%,74.00%,2.00%,45.00%,0.00%,3.9,1.86,1.09
18,58.35%,GPT-3.5-Turbo-0125 (FC),https://platform.openai.com/docs/models/gpt-3-5-turbo,OpenAI,Proprietary,70.52%,66.33%,57.09%,57.50%,53.00%,62.00%,65.50%,90.00%,69.50%,78.82%,81.00%,75.71%,70.00%,74.00%,42.50%,2.08%,0.42,1.26,0.68
19,58.12%,Mistral-small-2402 (FC Any),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,64.27%,46.94%,81.09%,90.25%,56.00%,58.00%,95.50%,39.00%,41.50%,81.76%,85.00%,77.14%,74.00%,12.00%,20.00%,0.00%,0.96,1.05,0.95
20,56.41%,Gemini-1.0-Pro (FC),https://deepmind.google/technologies/gemini/#introduction,Google,Proprietary,41.94%,38.57%,77.27%,89.75%,37.00%,58.00%,90.50%,0.00%,0.00%,75.29%,82.00%,65.71%,74.00%,0.00%,5.00%,77.50%,0.19,1.06,0.55
21,51.18%,FireFunction-v1 (FC),https://huggingface.co/fireworks-ai/firefunction-v1,Fireworks,Apache 2.0,39.94%,33.40%,67.27%,86.50%,13.00%,22.00%,92.50%,0.00%,0.00%,60.59%,79.00%,34.29%,68.00%,0.00%,5.00%,73.33%,N/A,1.24,1.2
22,51.06%,Nexusflow-Raven-v2 (FC),https://huggingface.co/Nexusflow/NexusRaven-V2-13B,Nexusflow,Apache 2.0,55.05%,57.22%,70.18%,76.00%,52.00%,60.00%,75.50%,30.50%,44.00%,55.88%,81.00%,20.00%,76.00%,52.00%,45.00%,2.08%,N/A,1.86,1.39
23,49.65%,GPT-4-0613 (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,38.53%,25.90%,61.64%,83.50%,4.00%,2.00%,92.50%,0.00%,0.00%,40.59%,58.00%,15.71%,58.00%,0.00%,5.00%,91.67%,10.48,3.54,3.37
24,48.71%,Mistral-tiny-2312 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,46.91%,28.71%,49.64%,61.75%,26.00%,0.00%,56.50%,47.50%,34.00%,22.35%,36.00%,2.86%,20.00%,50.00%,22.50%,82.08%,0.13,1.79,1.63
25,41.47%,Gemma-7b-it (Prompt),https://blog.google/technology/developers/gemma-open-models/,Google,gemma-terms-of-use,39.05%,33.15%,42.18%,47.75%,29.00%,24.00%,48.00%,30.00%,36.00%,30.59%,45.00%,10.00%,32.00%,40.00%,30.00%,60.42%,0.03,0.09,N/A
26,39.00%,Deepseek-v1.5 (Prompt),https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5,Deepseek,Deepseek License,36.98%,28.24%,38.91%,49.50%,4.00%,24.00%,48.50%,37.00%,23.50%,32.94%,38.00%,25.71%,36.00%,34.00%,10.00%,56.67%,0.45,1.2,N/A
27,37.65%,Mistral-Small-2402 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,37.66%,27.93%,5.64%,5.75%,6.00%,4.00%,8.00%,78.50%,58.50%,24.71%,4.00%,54.29%,0.00%,62.00%,25.00%,98.33%,0.7,1.09,0.95
28,32.47%,Mistral-Large-2402 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,28.92%,14.88%,14.18%,16.50%,3.00%,18.00%,13.50%,33.50%,54.50%,20.00%,8.00%,37.14%,8.00%,14.00%,17.50%,91.25%,1.11,1.72,1.04
29,17.53%,Mistral-small-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,2.53%,6.97%,1.64%,2.25%,0.00%,0.00%,2.50%,3.00%,3.00%,15.88%,16.00%,15.71%,12.00%,0.00%,0.00%,99.58%,2.02,2.93,1.61
2 changes: 1 addition & 1 deletion leaderboard.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,7 +191,7 @@ <h2>Error Type Analysis</h2>
<a href="blogs/8_berkeley_function_calling_leaderboard.html#metrics">evaluation metrics</a> and insight blog (coming soon).
</p>

<div id="0e086fa1-13be-408b-a557-107d06325345" class="plotly-graph-div" style="height:100%; width:100%;"></div>
<div id="924d403a-cbb4-4d1c-9424-e9916cf83b69" class="plotly-graph-div" style="height:100%; width:100%;"></div>
</div>

<!-- API Explorer Section -->
Expand Down
2 changes: 1 addition & 1 deletion treemap_2.js
View file
Open in desktop

Large diffs are not rendered by default.