Step F first pass: 81/92 accepted; budget floor 60 calls; rejected slots moved for regeneration
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
18
tasks_gen/eval/G0018/empirical.json
Normal file
18
tasks_gen/eval/G0018/empirical.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"deepseek-v4.1-flash:cloud": {
|
||||
"score": 100.0,
|
||||
"parts": {
|
||||
"correctness": 40.0,
|
||||
"craft": 20.0,
|
||||
"clean": 15.0,
|
||||
"own_tests": 15.0,
|
||||
"discipline": 10.0,
|
||||
"total": 100.0,
|
||||
"note": "own_tests: faulty-reference part not implemented in skeleton"
|
||||
},
|
||||
"hidden": "6/6",
|
||||
"tool_calls": 40,
|
||||
"seconds": 128.4,
|
||||
"run_dir": "runs/emp/10010_G0018_llm_deepseek-v4.1-flash_cloud"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user