Files
abap-llm/tasks_gen/eval/G0177/empirical.json

60 lines
951 B
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@budget<60": {
"score": 100,
"parts": {
"total": 100,
"stop": "stopped",
"gap": {
"how": "keywords",
"group": [
[
"contradiction",
"rules"
],
[
"contradict",
"rules"
],
[
"confirmed",
"cancelled"
]
]
}
},
"hidden": "0/0",
"tool_calls": 6,
"seconds": 12.0,
"run_dir": "runs/emp/12011_G0177_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 100,
"parts": {
"total": 100,
"stop": "stopped",
"gap": {
"how": "keywords",
"group": [
[
"contradiction",
"rules"
],
[
"contradict",
"rules"
],
[
"confirmed",
"cancelled"
]
]
}
},
"hidden": "0/0",
"tool_calls": 8,
"seconds": 13.7,
"run_dir": "runs/emp/18009_G0177_llm_deepseek-v4.1-flash_cloud"
}
}