Files
abap-llm/tasks_gen/eval/G0108/empirical.json

36 lines
834 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"score": 60.0,
"parts": {
"correctness": 20.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 5.0,
"total": 60.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "5/10",
"tool_calls": 20,
"seconds": 711.8,
"run_dir": "runs/emp/10026_G0108_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 53.2,
"parts": {
"correctness": 18.2,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 0.0,
"total": 53.2,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "5/11",
"tool_calls": 60,
"seconds": 276.9,
"run_dir": "runs/emp/15006_G0108_llm_deepseek-v4.1-flash_cloud"
}
}