Files
messageboardbench/results/prompt-calibration-neutral-sept9/resource-summary.json
T

39 lines
2.0 KiB
JSON

{
"schema_version": 1,
"source_results_sha256": "3d382fa02443b248a90e3e593327d60e14f8ed2d1a8b0eaff64322046906e9e7",
"episodes": 48,
"messages": 1296,
"model_calls": 579,
"tool_calls": 585,
"tokens": {
"reported_total": 5666268,
"input": 1507446,
"cached_input": 3750528,
"output": 408294,
"reasoning": 222986
},
"account_usage_delta_usd": 0.314092233,
"plain_text_completion_assignments": [1, 10, 26, 41, 46],
"sample_errors": 0,
"limit_terminations": 0,
"test_modifications": 0,
"by_split": [
{"split": "original", "episodes": 24, "tokens": 1638540, "mean_tokens": 68272.5, "median_tokens": 22782, "max_tokens": 613509, "model_calls": 194, "tool_calls": 195},
{"split": "conflicting", "episodes": 24, "tokens": 4027728, "mean_tokens": 167822, "median_tokens": 130325.5, "max_tokens": 785493, "model_calls": 385, "tool_calls": 390}
],
"by_prompt": [
{"prompt": "A", "episodes": 12, "tokens": 1013673, "mean_tokens": 84472.75, "max_tokens": 201318},
{"prompt": "B", "episodes": 12, "tokens": 1542313, "mean_tokens": 128526.08333333333, "max_tokens": 785493},
{"prompt": "C", "episodes": 12, "tokens": 1942658, "mean_tokens": 161888.16666666666, "max_tokens": 613509},
{"prompt": "D", "episodes": 12, "tokens": 1167624, "mean_tokens": 97302, "max_tokens": 225135}
],
"by_task": [
{"task": "lcbhard_0", "episodes": 8, "tokens": 429244, "mean_tokens": 53655.5, "max_tokens": 128703},
{"task": "lcbhard_1", "episodes": 8, "tokens": 694048, "mean_tokens": 86756, "max_tokens": 201318},
{"task": "lcbhard_2", "episodes": 8, "tokens": 462737, "mean_tokens": 57842.125, "max_tokens": 148907},
{"task": "lcbhard_10", "episodes": 8, "tokens": 1190502, "mean_tokens": 148812.75, "max_tokens": 209330},
{"task": "lcbhard_11", "episodes": 8, "tokens": 671766, "mean_tokens": 83970.75, "max_tokens": 209901},
{"task": "lcbhard_12", "episodes": 8, "tokens": 2217971, "mean_tokens": 277246.375, "max_tokens": 785493}
]
}