Files
abap-llm/tasks_gen/eval/G0131/empirical.json

36 lines
838 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"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": "10/10",
"tool_calls": 26,
"seconds": 718.5,
"run_dir": "runs/emp/10044_G0131_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": "10/10",
"tool_calls": 38,
"seconds": 143.9,
"run_dir": "runs/emp/16000_G0131_llm_deepseek-v4.1-flash_cloud"
}
}