Files
abap-llm/tasks_gen/eval/G0107/empirical.json

34 lines
724 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@g2-func-header-bug": {
"score": 0,
"parts": {
"total": 0,
"failed_gates": [
"G2_contract",
"G3_hidden_runs"
]
},
"hidden": "0/0",
"tool_calls": 31,
"seconds": 162.0,
"run_dir": "runs/emp/10025_G0107_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": "10/10",
"tool_calls": 18,
"seconds": 141.2,
"run_dir": "runs/emp/18011_G0107_llm_deepseek-v4.1-flash_cloud"
}
}