Files
abap-llm/tasks_gen/eval/G0191/empirical.json

36 lines
841 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@budget<60": {
"score": 100.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 10.0,
"total": 100.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "12/12",
"tool_calls": 8,
"seconds": 87.0,
"run_dir": "runs/emp/12000_G0191_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 100.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 10.0,
"total": 100.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "12/12",
"tool_calls": 24,
"seconds": 181.8,
"run_dir": "runs/emp/18010_G0191_llm_deepseek-v4.1-flash_cloud"
}
}