G0181 failure analysis (int8 in SALV), W7B results

This commit is contained in:
Kral
2026-10-03 19:16:56 +02:00
parent d8cbf4de25
commit e3f5dcd668
4 changed files with 47 additions and 0 deletions

View File

@@ -14,5 +14,21 @@
"seconds": 162.0,
"run_dir": "runs/emp/10025_G0107_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 85.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 10.0,
"total": 85.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "10/10",
"tool_calls": 18,
"seconds": 141.2,
"run_dir": "runs/emp/18011_G0107_llm_deepseek-v4.1-flash_cloud"
}
}

View File

@@ -13,5 +13,18 @@
"seconds": 55.8,
"run_dir": "runs/emp/12008_G0181_llm_deepseek-v4.1-flash_cloud"
}
},
"deepseek-v4.1-flash:cloud": {
"score": 0,
"parts": {
"total": 0,
"failed_gates": [
"G3_hidden_runs"
]
},
"hidden": "0/6",
"tool_calls": 58,
"seconds": 318.1,
"run_dir": "runs/emp/18012_G0181_llm_deepseek-v4.1-flash_cloud"
}
}

View File

@@ -16,5 +16,21 @@
"seconds": 87.0,
"run_dir": "runs/emp/12000_G0191_llm_deepseek-v4.1-flash_cloud"
}
},
"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": "12/12",
"tool_calls": 24,
"seconds": 181.8,
"run_dir": "runs/emp/18010_G0191_llm_deepseek-v4.1-flash_cloud"
}
}