Files
abap-llm/tasks_gen/eval/G0125/empirical.json

35 lines
732 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"score": 0,
"parts": {
"total": 0,
"failed_gates": [
"G1_active",
"G2_contract",
"G3_hidden_runs"
]
},
"hidden": "0/0",
"tool_calls": 18,
"seconds": 786.2,
"run_dir": "runs/emp/13000_G0125_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 80.0,
"parts": {
"correctness": 40.0,
"craft": 10.0,
"clean": 15.0,
"own_tests": 15.0,
"discipline": 0.0,
"total": 80.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "8/8",
"tool_calls": 47,
"seconds": 489.0,
"run_dir": "runs/emp/15014_G0125_llm_deepseek-v4.1-flash_cloud"
}
}