52 lines
1.2 KiB
JSON
52 lines
1.2 KiB
JSON
{
|
|
"_superseded": {
|
|
"deepseek-v4.1-flash:cloud@2026-10-03": {
|
|
"score": 75.0,
|
|
"parts": {
|
|
"correctness": 40.0,
|
|
"craft": 20.0,
|
|
"clean": 15.0,
|
|
"own_tests": 0.0,
|
|
"discipline": 0.0,
|
|
"total": 75.0,
|
|
"note": "own_tests: faulty-reference part not implemented in skeleton"
|
|
},
|
|
"hidden": "12/12",
|
|
"tool_calls": 13,
|
|
"seconds": 1043.6,
|
|
"run_dir": "runs/emp/12023_G0164_llm_deepseek-v4.1-flash_cloud"
|
|
},
|
|
"deepseek-v4.1-flash:cloud@budget<60": {
|
|
"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": 19,
|
|
"seconds": 424.7,
|
|
"run_dir": "runs/emp/16007_G0164_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": 13,
|
|
"seconds": 199.0,
|
|
"run_dir": "runs/emp/18003_G0164_llm_deepseek-v4.1-flash_cloud"
|
|
}
|
|
} |