Files
abap-llm/tasks_gen/eval/G0161/empirical.json

36 lines
834 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"score": 88.5,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 13.5,
"own_tests": 15.0,
"discipline": 0.0,
"total": 88.5,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "8/8",
"tool_calls": 60,
"seconds": 264.3,
"run_dir": "runs/emp/13005_G0161_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 95.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 5.0,
"total": 95.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "8/8",
"tool_calls": 29,
"seconds": 313.1,
"run_dir": "runs/emp/16006_G0161_llm_deepseek-v4.1-flash_cloud"
}
}