Files
abap-llm/tasks_gen/eval/G0180/empirical.json

18 lines
396 B
JSON

{
"deepseek-v4.1-flash:cloud": {
"score": 85.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 10.0,
"total": 85.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "10/10",
"tool_calls": 27,
"seconds": 140.5,
"run_dir": "runs/emp/12009_G0180_llm_deepseek-v4.1-flash_cloud"
}
}