Files
abap-llm/tasks_gen/eval/G0174/empirical.json

60 lines
1.0 KiB
JSON

{
"_superseded": {
"deepseek-v4.1-flash:cloud@2026-10-03": {
"score": 0,
"parts": {
"total": 0,
"stop": "implemented",
"objects": [
"Z099Q04U_FLOWER_SALES"
]
},
"hidden": "0/0",
"tool_calls": 12,
"seconds": 665.1,
"run_dir": "runs/emp/12014_G0174_llm_deepseek-v4.1-flash_cloud"
},
"deepseek-v4.1-flash:cloud@budget<60": {
"score": 100,
"parts": {
"total": 100,
"stop": "stopped",
"gap": {
"how": "keywords",
"group": [
[
"small",
"sale",
"defin"
]
]
}
},
"hidden": "0/0",
"tool_calls": 16,
"seconds": 78.1,
"run_dir": "runs/emp/16010_G0174_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 100,
"parts": {
"total": 100,
"stop": "stopped",
"gap": {
"how": "keywords",
"group": [
[
"small",
"sale",
"defin"
]
]
}
},
"hidden": "0/0",
"tool_calls": 17,
"seconds": 24.3,
"run_dir": "runs/emp/17008_G0174_llm_deepseek-v4.1-flash_cloud"
}
}