Files
abap-llm/tasks_gen/eval/G0190/empirical.json

36 lines
860 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"score": 90.0,
"parts": {
"correctness": 40.0,
"craft": 15.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 5.0,
"total": 90.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "7/7",
"tool_calls": 19,
"seconds": 852.8,
"run_dir": "runs/emp/12001_G0190_llm_deepseek-v4.1-flash_cloud"
},
"deepseek-v4.1-flash:cloud@budget<60": {
"score": 85.0,
"parts": {
"correctness": 40.0,
"craft": 10.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 5.0,
"total": 85.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "7/7",
"tool_calls": 22,
"seconds": 376.9,
"run_dir": "runs/emp/16013_G0190_llm_deepseek-v4.1-flash_cloud"
}
}
}