smol-developer-20230801081324

This commit is contained in:
Auto-GPT-Bot
2023-08-01 08:13:24 +00:00
parent d96aedd521
commit f0615f77ec
3 changed files with 80 additions and 60 deletions

View File

@@ -0,0 +1,14 @@
{
"command": "agbenchmark start",
"completion_time": "2023-08-01-08:13",
"benchmark_start_time": "2023-08-01-08:13",
"metrics": {
"run_time": "6.61 seconds",
"highest_difficulty": "No successful tests"
},
"tests": {},
"config": {
"workspace": "generated",
"entry_path": "agbenchmark.benchmarks"
}
}

View File

@@ -1 +1,6 @@
{}
{
"TestWriteFile": {
"difficulty": "interface",
"data_path": "agbenchmark/challenges/interface/write_file/data.json"
}
}

View File

@@ -1,63 +1,35 @@
{
"TestWriteFile": [
true,
true
],
"TestPlanCreation": [
true
],
"TestGoalDivergence": [
false
],
"TestSearch": [
false
],
"TestReadFile": [
false
],
"TestBasicRetrieval": [
false
],
"TestBasicContentGen": [
false
],
"TestReturnCode_Simple": [
false
],
"TestDebugSimpleTypoWithGuidance": [
false
],
"TestBasicMemory": [
false
],
"TestAdaptLink": [
false
],
"TestRevenueRetrieval_1.2": [
false
],
"TestRevenueRetrieval_1.1": [
false
],
"TestRevenueRetrieval_1.0": [
false
],
"TestReturnCode_Write": [
false
],
"TestDebugSimpleTypoWithoutGuidance": [
false
],
"TestAdaptSimpleTypoWithGuidance": [
false
],
"TestInstructionFollowing": [
"TestAdaptTeslaRevenue": [
false
],
"TestGoalLoss_Simple": [
"TestBasicContentGen": [
false
],
"TestGoalLoss_advanced": [
"TestBasicMemory": [
false
],
"TestBasicRetrieval": [
false
],
"TestDebugMultipleTypo": [
false
],
"TestDebugSimpleTypoWithGuidance": [
false
],
"TestDebugSimpleTypoWithoutGuidance": [
false
],
"TestFunctionCodeGeneration": [
false
],
"TestGoalDivergence": [
false
],
"TestGoalLoss_Hard": [
@@ -66,16 +38,25 @@
"TestGoalLoss_Medium": [
false
],
"TestGoalLoss_Simple": [
false
],
"TestGoalLoss_advanced": [
false
],
"TestInstructionFollowing": [
false
],
"TestPlanCreation": [
true
],
"TestReadFile": [
false
],
"TestRememberMultipleIds": [
false
],
"TestFunctionCodeGeneration": [
false
],
"TestReturnCode_Modify": [
false
],
"TestDebugMultipleTypo": [
"TestRememberMultiplePhrasesWithNoise": [
false
],
"TestRememberMultipleWithNoise": [
@@ -84,16 +65,36 @@
"TestRetrieval3": [
false
],
"TestAdaptTeslaRevenue": [
"TestReturnCode_Modify": [
false
],
"TestThreeSum": [
"TestReturnCode_Simple": [
false
],
"TestReturnCode_Tests": [
false
],
"TestRememberMultiplePhrasesWithNoise": [
"TestReturnCode_Write": [
false
],
"TestRevenueRetrieval_1.0": [
false
],
"TestRevenueRetrieval_1.1": [
false
],
"TestRevenueRetrieval_1.2": [
false
],
"TestSearch": [
false
],
"TestThreeSum": [
false
],
"TestWriteFile": [
true,
true,
true
]
}