Huanzhi Mao
commited on
Commit
·
0b85412
1
Parent(s):
bdd55a2
update data.csv, in sync with BFCL April 16th Release
Browse files
app.py
CHANGED
@@ -626,10 +626,10 @@ COLUMNS = [
|
|
626 |
"Parallel Functions Exec",
|
627 |
"Parallel Multiple Exec",
|
628 |
"Relevance Detection",
|
629 |
-
"Cost ($
|
630 |
"Latency Mean (s)",
|
631 |
-
"Latency
|
632 |
-
"Latency
|
633 |
"Organization",
|
634 |
"License",
|
635 |
]
|
|
|
626 |
"Parallel Functions Exec",
|
627 |
"Parallel Multiple Exec",
|
628 |
"Relevance Detection",
|
629 |
+
"Cost ($)",
|
630 |
"Latency Mean (s)",
|
631 |
+
"Latency SD (s)",
|
632 |
+
"Latency P95 (s)",
|
633 |
"Organization",
|
634 |
"License",
|
635 |
]
|
data.csv
CHANGED
@@ -1,31 +1,33 @@
|
|
1 |
Rank,Overall Acc,Model,Model Link,Organization,License,AST Summary,Exec Summary,Simple Function AST,Python Simple Function AST,Java Simple Function AST,JavaScript Simple Function AST,Multiple Functions AST,Parallel Functions AST,Parallel Multiple AST,Simple Function Exec,Python Simple Function Exec,REST Simple Function Exec,Multiple Functions Exec,Parallel Functions Exec,Parallel Multiple Exec,Relevance Detection,Cost ($ Per 1k Function Calls),Latency Mean (s),Latency Standard Deviation (s),Latency 95th Percentile (s)
|
2 |
-
1,
|
3 |
-
2,
|
4 |
-
3,81.
|
5 |
-
4,81.
|
6 |
-
5,
|
7 |
-
6,
|
8 |
-
7,
|
9 |
-
8,76
|
10 |
-
9,
|
11 |
-
10,
|
12 |
-
11,
|
13 |
-
12,
|
14 |
-
13,
|
15 |
-
14,65
|
16 |
-
15,
|
17 |
-
16,
|
18 |
-
17,
|
19 |
-
18,
|
20 |
-
19,58.
|
21 |
-
20,
|
22 |
-
21,
|
23 |
-
22,
|
24 |
-
23,
|
25 |
-
24,
|
26 |
-
25,
|
27 |
-
26,
|
28 |
-
27,
|
29 |
-
28,
|
30 |
-
29,
|
31 |
-
30,
|
|
|
|
|
|
1 |
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),Latency 95th Percentile (s)
|
2 |
+
1,84.41%,GPT-4-0125-Preview (Prompt),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,88.75%,71.54%,88.00%,94.25%,67.00%,80.00%,94.50%,90.50%,82.00%,91.18%,86.00%,98.57%,78.00%,72.00%,45.00%,70.42%,5.21,1.99,1.27,4.47
|
3 |
+
2,84.12%,Claude-3-Opus-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,86.09%,70.90%,86.36%,93.25%,66.00%,72.00%,93.50%,86.00%,78.50%,90.59%,87.00%,95.71%,76.00%,72.00%,45.00%,80.42%,10.8,5.05,1.78,7.54
|
4 |
+
3,81.88%,GPT-4-turbo-2024-04-09 (Prompt),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,86.83%,71.04%,85.82%,93.00%,60.00%,80.00%,94.50%,90.00%,77.00%,91.18%,86.00%,98.57%,80.00%,68.00%,45.00%,62.50%,5.22,2.68,2.41,6.43
|
5 |
+
4,81.76%,GPT-4-1106-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,84.75%,68.26%,82.00%,90.25%,61.00%,58.00%,91.00%,91.50%,74.50%,83.53%,85.00%,81.43%,70.00%,72.00%,47.50%,80.42%,5.03,6.34,6.04,18.29
|
6 |
+
5,81.71%,Gorilla-OpenFunctions-v2 (FC),https://gorilla.cs.berkeley.edu/blogs/7_open_functions_v2.html,Gorilla LLM,Apache 2.0,86.16%,71.52%,87.64%,94.25%,67.00%,76.00%,94.50%,87.50%,75.00%,90.59%,87.00%,95.71%,78.00%,70.00%,47.50%,60.83%,1.7,2.65,2.33,6.64
|
7 |
+
6,80.29%,GPT-4-0125-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,83.75%,66.13%,80.00%,90.25%,53.00%,52.00%,92.50%,90.00%,72.50%,73.53%,84.00%,58.57%,74.00%,72.00%,45.00%,82.92%,4.82,5.03,5.88,19.29
|
8 |
+
7,79.47%,Mistral-Medium-2312 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,81.44%,62.13%,79.27%,88.50%,54.00%,56.00%,92.50%,84.00%,70.00%,73.53%,86.00%,55.71%,70.00%,70.00%,35.00%,88.75%,1.75,2.77,2.27,6.31
|
9 |
+
8,78.76%,GPT-4-turbo-2024-04-09 (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,81.70%,65.13%,73.82%,90.00%,33.00%,26.00%,89.50%,89.00%,74.50%,73.53%,83.00%,60.00%,70.00%,72.00%,45.00%,88.75%,4.79,5.68,6.67,20.07
|
10 |
+
9,77.88%,Claude-3-Sonnet-20240229 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,85.20%,70.82%,81.82%,90.25%,53.00%,72.00%,88.50%,88.00%,82.50%,81.76%,75.00%,91.43%,78.00%,76.00%,47.50%,50.42%,2.12,2.11,1.15,3.16
|
11 |
+
10,77.12%,Functionary-Medium-v2.4 (FC),https://huggingface.co/meetkai/functionary-medium-v2.4,MeetKai,MIT,82.36%,62.61%,79.45%,88.00%,55.00%,60.00%,90.00%,87.50%,72.50%,62.94%,80.00%,38.57%,66.00%,74.00%,47.50%,74.17%,1.64,2.55,2.6,7.51
|
12 |
+
11,76.18%,Functionary-Small-v2.4 (FC),https://huggingface.co/meetkai/functionary-small-v2.4,MeetKai,MIT,80.00%,65.32%,80.00%,88.75%,56.00%,58.00%,89.00%,82.00%,69.00%,71.76%,81.00%,58.57%,68.00%,74.00%,47.50%,67.92%,1.76,2.74,2.47,7.29
|
13 |
+
12,73.71%,Claude-3-Opus-20240229 (FC tools-2024-04-04),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,70.35%,55.20%,80.91%,87.00%,61.00%,72.00%,91.00%,58.00%,51.50%,85.29%,85.00%,85.71%,74.00%,24.00%,37.50%,82.50%,30.65,12.63,3.64,19.72
|
14 |
+
13,73.00%,Claude-instant-1.2 (Prompt),https://www.anthropic.com/news/releasing-claude-instant-1-2,Anthropic,Proprietary,76.63%,64.08%,80.00%,87.25%,56.00%,70.00%,86.00%,83.00%,57.50%,78.82%,84.00%,71.43%,72.00%,58.00%,47.50%,54.17%,0.95,1.35,0.62,2.22
|
15 |
+
14,71.65%,Claude-3-Haiku-20240307 (Prompt),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,77.36%,64.26%,85.45%,94.25%,55.00%,76.00%,92.00%,84.00%,48.00%,87.06%,88.00%,85.71%,84.00%,46.00%,40.00%,29.58%,0.18,0.99,0.43,1.76
|
16 |
+
15,65.12%,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%,6.64,3.72,2.02,7.6
|
17 |
+
16,65.00%,Mistral-large-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,62.09%,47.35%,66.36%,88.75%,5.00%,10.00%,94.00%,25.50%,62.50%,69.41%,76.00%,60.00%,76.00%,4.00%,40.00%,84.17%,4.94,2.84,2.57,8.4
|
18 |
+
17,64.59%,DBRX-Instruct (Prompt),https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm,Databricks,Databricks Open Model,65.31%,64.10%,66.73%,79.50%,30.00%,38.00%,72.00%,72.00%,50.50%,69.41%,76.00%,60.00%,70.00%,72.00%,45.00%,56.25%,1.25,0.63,0.45,1.37
|
19 |
+
18,61.71%,Mistral-large-2402 (FC Any),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,68.98%,52.46%,82.91%,91.50%,62.00%,56.00%,93.00%,31.50%,68.50%,88.82%,84.00%,95.71%,74.00%,2.00%,45.00%,0.00%,3.9,1.86,1.09,4.28
|
20 |
+
19,58.94%,GPT-3.5-Turbo-0125 (FC),https://platform.openai.com/docs/models/gpt-3-5-turbo,OpenAI,Proprietary,70.52%,67.80%,57.09%,57.50%,53.00%,62.00%,65.50%,90.00%,69.50%,84.71%,81.00%,90.00%,70.00%,74.00%,42.50%,2.08%,0.42,1.26,0.68,2.45
|
21 |
+
20,58.71%,Mistral-small-2402 (FC Any),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,64.27%,48.41%,81.09%,90.25%,56.00%,58.00%,95.50%,39.00%,41.50%,87.65%,85.00%,91.43%,74.00%,12.00%,20.00%,0.00%,0.96,1.05,0.95,2.31
|
22 |
+
21,58.41%,Hermes-2-Pro-Mistral-7B (FC),https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B,NousResearch,apache-2.0,67.99%,54.26%,71.45%,81.00%,42.00%,54.00%,81.00%,66.50%,53.00%,57.06%,79.00%,25.71%,70.00%,50.00%,40.00%,10.83%,0.15,0.39,N/A,N/A
|
23 |
+
22,58.06%,Claude-3-Sonnet-20240229 (FC tools-2024-04-04),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,44.06%,38.66%,76.73%,86.00%,49.00%,58.00%,87.50%,6.00%,6.00%,77.65%,86.00%,65.71%,72.00%,0.00%,5.00%,81.67%,3.41,3.35,1.47,6.93
|
24 |
+
23,56.94%,Gemini-1.0-Pro (FC),https://deepmind.google/technologies/gemini/#introduction,Google,Proprietary,41.94%,39.90%,77.27%,89.75%,37.00%,58.00%,90.50%,0.00%,0.00%,80.59%,81.00%,80.00%,74.00%,0.00%,5.00%,77.50%,0.19,1.06,0.55,1.67
|
25 |
+
24,52.59%,Claude-3-Haiku-20240307 (FC tools-2024-04-04),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,44.69%,42.72%,85.27%,94.25%,60.00%,64.00%,93.00%,0.50%,0.00%,85.88%,86.00%,85.71%,80.00%,0.00%,5.00%,20.83%,0.29,1.52,0.64,2.31
|
26 |
+
25,51.53%,FireFunction-v1 (FC),https://huggingface.co/fireworks-ai/firefunction-v1,Fireworks,Apache 2.0,39.94%,34.28%,67.27%,86.50%,13.00%,22.00%,92.50%,0.00%,0.00%,64.12%,79.00%,42.86%,68.00%,0.00%,5.00%,73.33%,N/A,1.24,1.2,3.26
|
27 |
+
26,50.94%,Nexusflow-Raven-v2 (FC),https://huggingface.co/Nexusflow/NexusRaven-V2-13B,Nexusflow,Apache 2.0,55.05%,56.93%,70.18%,76.00%,52.00%,60.00%,75.50%,30.50%,44.00%,54.71%,79.00%,20.00%,76.00%,52.00%,45.00%,2.08%,N/A,1.86,1.39,4.45
|
28 |
+
27,49.71%,GPT-4-0613 (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,38.53%,26.04%,61.64%,83.50%,4.00%,2.00%,92.50%,0.00%,0.00%,41.18%,57.00%,18.57%,58.00%,0.00%,5.00%,91.67%,10.48,3.54,3.37,11.15
|
29 |
+
28,48.71%,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%,0.13,1.79,1.63,5.12
|
30 |
+
29,41.47%,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,N/A
|
31 |
+
30,39.41%,Deepseek-v1.5 (Prompt),https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5,Deepseek,Deepseek License,36.98%,29.26%,38.91%,49.50%,4.00%,24.00%,48.50%,37.00%,23.50%,37.06%,38.00%,35.71%,36.00%,34.00%,10.00%,56.67%,0.45,1.2,N/A,N/A
|
32 |
+
31,38.18%,Mistral-Small-2402 (Prompt),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,37.66%,29.25%,5.64%,5.75%,6.00%,4.00%,8.00%,78.50%,58.50%,30.00%,4.00%,67.14%,0.00%,62.00%,25.00%,98.33%,0.7,1.09,0.95,2.94
|
33 |
+
32,17.65%,Mistral-small-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,2.53%,7.26%,1.64%,2.25%,0.00%,0.00%,2.50%,3.00%,3.00%,17.06%,16.00%,18.57%,12.00%,0.00%,0.00%,99.58%,2.02,2.93,1.61,5.79
|