Files
abap-llm/tasks_gen/eval/G0022/empirical.json

18 lines
396 B
JSON

{
"deepseek-v4.1-flash:cloud": {
"score": 95.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 5.0,
"total": 95.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "13/13",
"tool_calls": 32,
"seconds": 141.5,
"run_dir": "runs/emp/10014_G0022_llm_deepseek-v4.1-flash_cloud"
}
}