Files
abap-llm/tasks_gen/eval/G0019/empirical.json

36 lines
833 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"score": 80.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 5.0,
"total": 80.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "8/8",
"tool_calls": 36,
"seconds": 680.7,
"run_dir": "runs/emp/10011_G0019_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 90.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 0.0,
"total": 90.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "9/9",
"tool_calls": 58,
"seconds": 392.1,
"run_dir": "runs/emp/15002_G0019_llm_deepseek-v4.1-flash_cloud"
}
}