84 lines
2.2 KiB
JSON
84 lines
2.2 KiB
JSON
{
|
|
"date": "2026-10-20",
|
|
"baseline": "bug20-joint-planning-20261019.json",
|
|
"candidate": "bug20-startup-batch-20261020-g00000067.json",
|
|
"old_three_verbose_starts": {
|
|
"call_count": 3,
|
|
"input_tokens": {
|
|
"known_sum": 23929,
|
|
"missing_call_count": 0
|
|
},
|
|
"output_tokens": {
|
|
"known_sum": 12476,
|
|
"missing_call_count": 0
|
|
},
|
|
"reasoning_tokens": {
|
|
"known_sum": 11263,
|
|
"missing_call_count": 0
|
|
},
|
|
"visible_output_tokens": {
|
|
"known_sum": 1213,
|
|
"missing_call_count": 0
|
|
},
|
|
"cached_input_tokens": {
|
|
"known_sum": 15375,
|
|
"missing_call_count": 0
|
|
},
|
|
"api_elapsed_seconds_sum": 125.891
|
|
},
|
|
"new_three_lean_queries": {
|
|
"call_count": 3,
|
|
"input_tokens": {
|
|
"known_sum": 33087,
|
|
"missing_call_count": 0
|
|
},
|
|
"output_tokens": {
|
|
"known_sum": 8508,
|
|
"missing_call_count": 0
|
|
},
|
|
"reasoning_tokens": {
|
|
"known_sum": 8207,
|
|
"missing_call_count": 0
|
|
},
|
|
"visible_output_tokens": {
|
|
"known_sum": 301,
|
|
"missing_call_count": 0
|
|
},
|
|
"cached_input_tokens": {
|
|
"known_sum": 23553,
|
|
"missing_call_count": 0
|
|
},
|
|
"api_elapsed_seconds_sum": 63.813
|
|
},
|
|
"new_queries_plus_joint_review": {
|
|
"call_count": 4,
|
|
"input_tokens": {
|
|
"known_sum": 42529,
|
|
"missing_call_count": 0
|
|
},
|
|
"output_tokens": {
|
|
"known_sum": 11461,
|
|
"missing_call_count": 0
|
|
},
|
|
"reasoning_tokens": {
|
|
"known_sum": 10446,
|
|
"missing_call_count": 0
|
|
},
|
|
"visible_output_tokens": {
|
|
"known_sum": 1015,
|
|
"missing_call_count": 0
|
|
},
|
|
"cached_input_tokens": {
|
|
"known_sum": 25613,
|
|
"missing_call_count": 0
|
|
},
|
|
"api_elapsed_seconds_sum": 86.017
|
|
},
|
|
"limitations": [
|
|
"Different individual runs and different queries, not a controlled paired benchmark",
|
|
"The new joint review settles all initial results; the three old startup calls left own result assessments for subsequent loop calls",
|
|
"Includes joint review cost; excludes planning, name resolution, later investigation and any final diagnosis",
|
|
"No final euro cost reported yet; input/cache/storage pricing must be considered separately"
|
|
]
|
|
}
|