Files
abap-llm/tasks_gen/eval/G0185/empirical.json

18 lines
394 B
JSON

{
"deepseek-v4.1-flash:cloud": {
"score": 50.9,
"parts": {
"correctness": 10.9,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 5.0,
"total": 50.9,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "3/11",
"tool_calls": 17,
"seconds": 589.5,
"run_dir": "runs/emp/12004_G0185_llm_deepseek-v4.1-flash_cloud"
}
}