erhan/abap-llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Review: 9 random high-score checks; easy candidates list

Browse Source
This commit is contained in:
Kral
2026-10-03 18:56:12 +02:00
parent 22022ca6a5
commit fb18dc8d9d
10 changed files with 54 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
tasks_gen/eval/easy_candidates.json Normal file
View File

@@ -0,0 +1,45 @@
{
"rule": "DeepSeek (budget 60) score >= 95 and tool_calls <= 20, outcome implement; candidate only until the Qwen baseline confirms",
"date": "2026-10-03",
"tasks": [
"G0003",
"G0004",
"G0007",
"G0008",
"G0010",
"G0100",
"G0101",
"G0103",
"G0104",
"G0113",
"G0114",
"G0115",
"G0116",
"G0117",
"G0118",
"G0120",
"G0127",
"G0129",
"G0130",
"G0135",
"G0136",
"G0137",
"G0138",
"G0139",
"G0141",
"G0142",
"G0148",
"G0149",
"G0150",
"G0151",
"G0159",
"G0163",
"G0164",
"G0167",
"G0178",
"G0179",
"G0186",
"G0187",
"G0188"
]
}