Runner: G2 finds the FUNCTION statement after local classes; budget floor applied to all tasks
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
@@ -1,18 +1,36 @@
|
||||
{
|
||||
"deepseek-v4.1-flash:cloud": {
|
||||
"score": 90.0,
|
||||
"parts": {
|
||||
"correctness": 40.0,
|
||||
"craft": 15.0,
|
||||
"clean": 15.0,
|
||||
"own_tests": 15.0,
|
||||
"discipline": 5.0,
|
||||
"total": 90.0,
|
||||
"note": "own_tests: faulty-reference part not implemented in skeleton"
|
||||
"_superseded": {
|
||||
"deepseek-v4.1-flash:cloud@2026-10-03": {
|
||||
"score": 90.0,
|
||||
"parts": {
|
||||
"correctness": 40.0,
|
||||
"craft": 15.0,
|
||||
"clean": 15.0,
|
||||
"own_tests": 15.0,
|
||||
"discipline": 5.0,
|
||||
"total": 90.0,
|
||||
"note": "own_tests: faulty-reference part not implemented in skeleton"
|
||||
},
|
||||
"hidden": "7/7",
|
||||
"tool_calls": 19,
|
||||
"seconds": 852.8,
|
||||
"run_dir": "runs/emp/12001_G0190_llm_deepseek-v4.1-flash_cloud"
|
||||
},
|
||||
"hidden": "7/7",
|
||||
"tool_calls": 19,
|
||||
"seconds": 852.8,
|
||||
"run_dir": "runs/emp/12001_G0190_llm_deepseek-v4.1-flash_cloud"
|
||||
"deepseek-v4.1-flash:cloud@budget<60": {
|
||||
"score": 85.0,
|
||||
"parts": {
|
||||
"correctness": 40.0,
|
||||
"craft": 10.0,
|
||||
"clean": 15.0,
|
||||
"own_tests": 15.0,
|
||||
"discipline": 5.0,
|
||||
"total": 85.0,
|
||||
"note": "own_tests: faulty-reference part not implemented in skeleton"
|
||||
},
|
||||
"hidden": "7/7",
|
||||
"tool_calls": 22,
|
||||
"seconds": 376.9,
|
||||
"run_dir": "runs/emp/16013_G0190_llm_deepseek-v4.1-flash_cloud"
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -6,8 +6,8 @@
|
||||
"release_target": "v816",
|
||||
"expected_outcome": "implement",
|
||||
"budget": {
|
||||
"max_tool_calls": 40,
|
||||
"max_activations": 10
|
||||
"max_tool_calls": 60,
|
||||
"max_activations": 15
|
||||
},
|
||||
"seed": [
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user