diff options
Diffstat (limited to 'benchmark/reports/mini-agi/14_TestReturnCode.json')
-rw-r--r-- | benchmark/reports/mini-agi/14_TestReturnCode.json | 99 |
1 files changed, 99 insertions, 0 deletions
diff --git a/benchmark/reports/mini-agi/14_TestReturnCode.json b/benchmark/reports/mini-agi/14_TestReturnCode.json new file mode 100644 index 000000000..653af76a1 --- /dev/null +++ b/benchmark/reports/mini-agi/14_TestReturnCode.json @@ -0,0 +1,99 @@ +{ + "command": "agbenchmark start --suite TestReturnCode", + "completion_time": "2023-07-22-23:49", + "metrics": { + "run_time": "16.31 seconds", + "highest_difficulty": "No successful tests" + }, + "tests": { + "TestReturnCode": { + "data_path": "agbenchmark/challenges/code/c1_writing_suite_1", + "metrics": { + "percentage": 0.0, + "highest_difficulty": "No successful tests", + "run_time": "15.972 seconds" + }, + "tests": { + "TestReturnCode_Simple": { + "data_path": "agbenchmark/challenges/code/c1_writing_suite_1/1_return/data.json", + "is_regression": false, + "category": [ + "code", + "iterate" + ], + "task": "Return the multiplied number in the function multiply_int in code.py. You can make sure you have correctly done this by running test.py", + "answer": "Just a simple multiple by 2 function. Num is 4 so answer is 8", + "description": "Simple test if a simple code instruction can be executed", + "metrics": { + "difficulty": "basic", + "success": false, + "fail_reason": "assert 1 in [0.0]", + "success_%": 0.0, + "run_time": "15.96 seconds" + }, + "reached_cutoff": false + }, + "TestReturnCode_Write": { + "data_path": "agbenchmark/challenges/code/c1_writing_suite_1/2_write/data.json", + "is_regression": false, + "category": [ + "code", + "iterate" + ], + "task": "Add a function called multiply_int in code.py that multiplies numbers by 2. You can make sure you have correctly done this by running test.py", + "answer": "Just a simple multiple by 2 function. Num is 4 so answer is 8", + "description": "Small step up, just writing the function with a name as well as the return statement.", + "metrics": { + "difficulty": "novice", + "success": false, + "fail_reason": "agbenchmark/challenges/test_all.py::TestReturnCode_Write::test_method[challenge_data0] depends on agbenchmark/challenges/test_all.py::TestReturnCode_Simple::test_method[challenge_data0]", + "success_%": 0.0, + "run_time": "0.004 seconds" + }, + "reached_cutoff": false + }, + "TestReturnCode_Modify": { + "data_path": "agbenchmark/challenges/code/c1_writing_suite_1/3_modify/data.json", + "is_regression": false, + "category": [ + "code", + "iterate" + ], + "task": "Modify the multiply_int function in code.py to be able to pass in a 'multiplier' argument to multiply the 'num' by 'multiplier'. Both arguments are integers. You can make sure you have correctly done this by running test.py", + "answer": "def multiply_int(num, multiplier):\n return num * multiplier\n", + "description": "Builds on the previous function also take a multiplier .", + "metrics": { + "difficulty": "intermediate", + "success": false, + "fail_reason": "agbenchmark/challenges/test_all.py::TestReturnCode_Modify::test_method[challenge_data0] depends on agbenchmark/challenges/test_all.py::TestReturnCode_Write::test_method[challenge_data0]", + "success_%": 0.0, + "run_time": "0.004 seconds" + }, + "reached_cutoff": false + }, + "TestReturnCode_Tests": { + "data_path": "agbenchmark/challenges/code/c1_writing_suite_1/4_tests/data.json", + "is_regression": false, + "category": [ + "code", + "iterate" + ], + "task": "First, modify test.py to fill in the test case to be able to test the code in code.py. Next, modify the multiply_int function in code.py to be able to pass in a 'multiplier' argument to multiply the 'num' by 'multiplier'. Both arguments are integers. You can make sure you have correctly done this by running test.py that you previously modified.", + "answer": "Just a simple multiple by 2 function. Num is 4 so answer is 8", + "description": "Small step up, just writing the function with a name as well as the return statement.", + "metrics": { + "difficulty": "advanced", + "success": false, + "fail_reason": "agbenchmark/challenges/test_all.py::TestReturnCode_Tests::test_method[challenge_data0] depends on agbenchmark/challenges/test_all.py::TestReturnCode_Modify::test_method[challenge_data0]", + "success_%": 0.0, + "run_time": "0.004 seconds" + }, + "reached_cutoff": false + } + } + } + }, + "config": { + "workspace": "${os.path.join(Path.home(), 'miniagi')}" + } +}
\ No newline at end of file |