Files
abap-llm/tasks_gen/eval/G0024/empirical.json

36 lines
833 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"score": 92.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 12.0,
"own_tests": 15.0,
"discipline": 5.0,
"total": 92.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "7/7",
"tool_calls": 32,
"seconds": 691.7,
"run_dir": "runs/emp/11003_G0024_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"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": "7/7",
"tool_calls": 60,
"seconds": 232.0,
"run_dir": "runs/emp/15004_G0024_llm_deepseek-v4.1-flash_cloud"
}
}