Files
abap-llm/tasks_gen/eval/G0159/empirical.json

36 lines
838 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@budget<60": {
"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": 11,
"seconds": 36.2,
"run_dir": "runs/emp/11029_G0159_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 100.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 10.0,
"total": 100.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "10/10",
"tool_calls": 10,
"seconds": 62.0,
"run_dir": "runs/emp/17002_G0159_llm_deepseek-v4.1-flash_cloud"
}
}