Huanzhi Mao commited on
Commit
23ba85c
1 Parent(s): d4c7482

update data to include more models

Browse files
Files changed (1) hide show
  1. data.csv +7 -7
data.csv CHANGED
@@ -1,6 +1,6 @@
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)
2
  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
3
- 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%,5.22,2.10,1.4
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
5
  4,78.18%,GPT-4-0125-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,81.23%,63.88%,78.91%,88.75%,55.00%,48.00%,91.00%,88.50%,66.50%,70.00%,82.00%,52.86%,68.00%,70.00%,47.50%,81.67%,4.76,4.37,5.31
6
  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
@@ -8,8 +8,8 @@ Rank,Overall Acc,Model,Model Link,Organization,License,AST Summary,Exec Summary,
8
  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
9
  8,69.18%,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%,0.95,1.75,1.0
10
  9,68.24%,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%,26.58,14.82,6.0
11
- 10,64.06%,Claude-3-Sonnet-20240229 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,66.52%,59.26%,69.09%,78.50%,38.00%,56.00%,70.50%,72.50%,54.00%,63.53%,83.00%,35.71%,68.00%,68.00%,37.50%,51.67%,5.08,6.70,3.07
12
- 11,63.65%,Claude-2.1 (Prompt),https://www.anthropic.com/news/claude-2-1,Anthropic,Proprietary,59.47%,45.68%,74.36%,80.00%,59.00%,60.00%,72.50%,55.00%,36.00%,48.24%,61.00%,30.00%,66.00%,36.00%,32.50%,83.33%,6.62,3.20,1.42
13
  12,62.53%,Mistral-large-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,57.60%,47.33%,64.91%,88.00%,3.00%,4.00%,88.50%,22.50%,54.50%,68.82%,75.00%,60.00%,72.00%,6.00%,42.50%,84.17%,4.74,2.91,2.73
14
  13,62.00%,Claude-3-Haiku-20240307 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,71.22%,57.65%,74.36%,84.25%,49.00%,46.00%,76.00%,76.00%,58.50%,50.59%,82.00%,5.71%,72.00%,68.00%,40.00%,21.67%,0.44,3.81,2.32
15
  14,60.65%,DBRX-Instruct (Prompt),https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm,Databricks,Databricks Open Model,62.20%,59.25%,61.82%,72.75%,26.00%,46.00%,73.00%,70.00%,44.00%,60.00%,77.00%,35.71%,72.00%,60.00%,45.00%,54.58%,1.24,0.62,0.41
@@ -17,11 +17,11 @@ Rank,Overall Acc,Model,Model Link,Organization,License,AST Summary,Exec Summary,
17
  16,56.65%,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
18
  17,55.82%,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
19
  18,54.82%,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
20
- 19,50.18%,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,1.90,1.57
21
- 20,49.88%,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
22
  21,47.94%,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
23
  22,46.35%,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
24
- 23,39.29%,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%,0.04,0.09,N/A
25
- 24,37.12%,Deepseek-v1.5 (Prompt),https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5,Deepseek,Deepseek License,33.51%,30.05%,36.55%,45.25%,7.00%,26.00%,41.00%,33.00%,23.50%,34.71%,39.00%,28.57%,38.00%,30.00%,17.50%,56.25%,0.45,1.20,N/A
26
  25,29.76%,Glaive-v1 (FC),https://huggingface.co/glaiveai/glaive-function-calling-v1,Glaive,cc-by-sa-4.0,28.84%,0.00%,52.36%,70.25%,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
27
  26,17.82%,Mistral-small-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,2.52%,7.65%,1.09%,1.50%,0.00%,0.00%,3.00%,4.00%,2.00%,20.59%,18.00%,24.29%,10.00%,0.00%,0.00%,99.58%,1.99,2.82,1.43
 
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)
2
  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
3
+ 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
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
5
  4,78.18%,GPT-4-0125-Preview (FC),https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo,OpenAI,Proprietary,81.23%,63.88%,78.91%,88.75%,55.00%,48.00%,91.00%,88.50%,66.50%,70.00%,82.00%,52.86%,68.00%,70.00%,47.50%,81.67%,4.76,4.37,5.31
6
  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
 
8
  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
9
  8,69.18%,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%,0.95,1.75,1.0
10
  9,68.24%,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%,26.58,14.82,6.0
11
+ 10,64.06%,Claude-3-Sonnet-20240229 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,66.52%,59.26%,69.09%,78.50%,38.00%,56.00%,70.50%,72.50%,54.00%,63.53%,83.00%,35.71%,68.00%,68.00%,37.50%,51.67%,5.08,6.7,3.07
12
+ 11,63.65%,Claude-2.1 (Prompt),https://www.anthropic.com/news/claude-2-1,Anthropic,Proprietary,59.47%,45.68%,74.36%,80.00%,59.00%,60.00%,72.50%,55.00%,36.00%,48.24%,61.00%,30.00%,66.00%,36.00%,32.50%,83.33%,6.62,3.2,1.42
13
  12,62.53%,Mistral-large-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,57.60%,47.33%,64.91%,88.00%,3.00%,4.00%,88.50%,22.50%,54.50%,68.82%,75.00%,60.00%,72.00%,6.00%,42.50%,84.17%,4.74,2.91,2.73
14
  13,62.00%,Claude-3-Haiku-20240307 (FC),https://www.anthropic.com/news/claude-3-family,Anthropic,Proprietary,71.22%,57.65%,74.36%,84.25%,49.00%,46.00%,76.00%,76.00%,58.50%,50.59%,82.00%,5.71%,72.00%,68.00%,40.00%,21.67%,0.44,3.81,2.32
15
  14,60.65%,DBRX-Instruct (Prompt),https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm,Databricks,Databricks Open Model,62.20%,59.25%,61.82%,72.75%,26.00%,46.00%,73.00%,70.00%,44.00%,60.00%,77.00%,35.71%,72.00%,60.00%,45.00%,54.58%,1.24,0.62,0.41
 
17
  16,56.65%,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
18
  17,55.82%,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
19
  18,54.82%,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
20
+ 19,50.18%,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
21
+ 20,49.88%,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
22
  21,47.94%,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
23
  22,46.35%,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
24
+ 23,39.29%,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
25
+ 24,37.12%,Deepseek-v1.5 (Prompt),https://huggingface.co/deepseek-ai/deepseek-coder-7b-instruct-v1.5,Deepseek,Deepseek License,33.51%,30.05%,36.55%,45.25%,7.00%,26.00%,41.00%,33.00%,23.50%,34.71%,39.00%,28.57%,38.00%,30.00%,17.50%,56.25%,0.45,1.2,N/A
26
  25,29.76%,Glaive-v1 (FC),https://huggingface.co/glaiveai/glaive-function-calling-v1,Glaive,cc-by-sa-4.0,28.84%,0.00%,52.36%,70.25%,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
27
  26,17.82%,Mistral-small-2402 (FC Auto),https://docs.mistral.ai/guides/model-selection/,Mistral AI,Proprietary,2.52%,7.65%,1.09%,1.50%,0.00%,0.00%,3.00%,4.00%,2.00%,20.59%,18.00%,24.29%,10.00%,0.00%,0.00%,99.58%,1.99,2.82,1.43