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

36 lines
835 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"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"
}
},
"deepseek-v4.1-flash:cloud": {
"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": "11/11",
"tool_calls": 20,
"seconds": 55.8,
"run_dir": "runs/emp/16012_G0185_llm_deepseek-v4.1-flash_cloud"
}
}