173 lines
8.1 KiB
JSON
173 lines
8.1 KiB
JSON
|
{
|
||
|
|
"command": "agbenchmark start",
|
||
|
|
"completion_time": "2023-07-18-00:25",
|
||
|
|
"metrics": {
|
||
|
|
"run_time": "493.76 seconds",
|
||
|
|
"highest_difficulty": "intermediate: 4"
|
||
|
|
},
|
||
|
|
"tests": {
|
||
|
|
"TestWriteFile": {
|
||
|
|
"data_path": "agbenchmark/challenges/interface/write_file",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "interface",
|
||
|
|
"success": true,
|
||
|
|
"success_%": 100.0,
|
||
|
|
"run_time": "66.807 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestBasicCodeGeneration": {
|
||
|
|
"data_path": "agbenchmark/challenges/code/d4",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "novice",
|
||
|
|
"success": true,
|
||
|
|
"success_%": 100.0,
|
||
|
|
"run_time": "84.302 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestSearch": {
|
||
|
|
"data_path": "agbenchmark/challenges/interface/search",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "interface",
|
||
|
|
"success": true,
|
||
|
|
"success_%": 100.0,
|
||
|
|
"run_time": "74.761 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestReadFile": {
|
||
|
|
"data_path": "agbenchmark/challenges/interface/read_file",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "interface",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "[Errno 2] No such file or directory: '/home/runner/work/Auto-GPT-Benchmarks/Auto-GPT-Benchmarks/agent/gpt-engineer/projects/my-new-project/workspace/file_to_check.txt'",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "45.324 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestThreeSum": {
|
||
|
|
"data_path": "agbenchmark/challenges/code/d5",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "intermediate",
|
||
|
|
"success": true,
|
||
|
|
"success_%": 100.0,
|
||
|
|
"run_time": "86.25 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestBasicRetrieval": {
|
||
|
|
"data_path": "agbenchmark/challenges/retrieval/r1",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "basic",
|
||
|
|
"success": true,
|
||
|
|
"success_%": 100.0,
|
||
|
|
"run_time": "76.728 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestDebugSimpleTypoWithGuidance": {
|
||
|
|
"data_path": "agbenchmark/challenges/code/d1",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "basic",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithGuidance::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestReadFile::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestBasicMemory": {
|
||
|
|
"data_path": "agbenchmark/challenges/memory/m1",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "basic",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestBasicMemory::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestReadFile::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestRetrieval2": {
|
||
|
|
"data_path": "agbenchmark/challenges/retrieval/r2",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "novice",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "assert 1 in [0.0, 0.0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "59.412 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestCreateSimpleWebServer": {
|
||
|
|
"data_path": "agbenchmark/challenges/code/d3",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "advanced",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestCreateSimpleWebServer::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithGuidance::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestDebugSimpleTypoWithoutGuidance": {
|
||
|
|
"data_path": "agbenchmark/challenges/code/d2",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "novice",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithoutGuidance::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestDebugSimpleTypoWithGuidance::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestRememberMultipleIds": {
|
||
|
|
"data_path": "agbenchmark/challenges/memory/m2",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "novice",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIds::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestBasicMemory::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestRetrieval3": {
|
||
|
|
"data_path": "agbenchmark/challenges/retrieval/r3",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "intermediate",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRetrieval3::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRetrieval2::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestRememberMultipleIdsWithNoise": {
|
||
|
|
"data_path": "agbenchmark/challenges/memory/m3",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "intermediate",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIdsWithNoise::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIds::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"TestRememberMultiplePhrasesWithNoise": {
|
||
|
|
"data_path": "agbenchmark/challenges/memory/m4",
|
||
|
|
"is_regression": false,
|
||
|
|
"metrics": {
|
||
|
|
"difficulty": "advanced",
|
||
|
|
"success": false,
|
||
|
|
"fail_reason": "agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultiplePhrasesWithNoise::test_method[challenge_data0] depends on agent/gpt-engineer/venv/lib/python3.10/site-packages/agbenchmark/challenges/test_all.py::TestRememberMultipleIdsWithNoise::test_method[challenge_data0]",
|
||
|
|
"success_%": 0.0,
|
||
|
|
"run_time": "0.001 seconds"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"config": {
|
||
|
|
"workspace": "projects/my-new-project/workspace"
|
||
|
|
}
|
||
|
|
}
|