diff --git a/benchmark/swe-bench-lite.txt b/benchmark/swe-bench-lite.txt new file mode 100644 index 000000000..b61c44c30 --- /dev/null +++ b/benchmark/swe-bench-lite.txt @@ -0,0 +1,44 @@ +model: gpt-3.5-turbo +validate_environment: {'keys_in_environment': True, 'missing_keys': []} +completion: Hello! How can I assist you today? + +model: claude-3-sonnet-20240229 +validate_environment: {'keys_in_environment': True, 'missing_keys': []} +completion: Hello! How can I assist you today? + +model: gemini/gemini-1.5-pro-latest +validate_environment: {'keys_in_environment': False, 'missing_keys': []} +completion: Hello! 👋 How can I help you today? 😊 + + +model: command-r-plus +validate_environment: {'keys_in_environment': False, 'missing_keys': []} +completion: Hello! How can I help you today? + +erased environment + +model: gpt-3.5-turbo +validate_environment: {'keys_in_environment': False, 'missing_keys': ['OPENAI_API_KEY']} +completion error: OpenAIException - Traceback (most recent call last): + File "/Users/gauthier/Projects/aider/.venv/lib/python3.11/site-packages/litellm/llms/openai.py", line 414, in completion + raise e + File "/Users/gauthier/Projects/aider/.venv/lib/python3.11/site-packages/litellm/llms/openai.py", line 350, in completion + openai_client = openai( + ^^^^^^^ + File "/Users/gauthier/Projects/aider/.venv/lib/python3.11/site-packages/openai/_client.py", line 104, in __init__ + raise openaiError( +openai.openaiError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable + + +model: claude-3-sonnet-20240229 +validate_environment: {'keys_in_environment': False, 'missing_keys': ['ANTHROPIC_API_KEY']} +completion error: Missing Anthropic API Key - A call is being made to anthropic but no key is set either in the environment variables or via params + +model: gemini/gemini-1.5-pro-latest +validate_environment: {'keys_in_environment': False, 'missing_keys': []} +completion error: PalmException - Invalid api key + +model: command-r-plus +validate_environment: {'keys_in_environment': False, 'missing_keys': []} +completion error: {"message":"no api key supplied"} + diff --git a/benchmark/swe_bench_lite.py b/benchmark/swe_bench_lite.py index 72106f197..afa76c1d4 100644 --- a/benchmark/swe_bench_lite.py +++ b/benchmark/swe_bench_lite.py @@ -68,4 +68,4 @@ def plot_swe_bench_lite(data_file): # Example usage -plot_swe_bench_lite("benchmark/tmp.txt") +plot_swe_bench_lite("benchmark/swe-bench-lite.txt")