mirror of
https://github.com/priyanshujain/messageboardbench.git
synced 2026-10-02 19:17:07 +00:00
170 lines
4.6 KiB
JSON
170 lines
4.6 KiB
JSON
{
|
|
"all": {
|
|
"episodes": 12,
|
|
"scorer_passes": 12,
|
|
"errors": 0,
|
|
"limits": 0,
|
|
"totals": {
|
|
"total_tokens": 2368733,
|
|
"input_tokens": 240193,
|
|
"cache_read_tokens": 1985748,
|
|
"cache_write_tokens": null,
|
|
"output_tokens": 142792,
|
|
"reasoning_tokens": 91646,
|
|
"working_seconds": 1677.025,
|
|
"model_calls": 160,
|
|
"submit_tool_calls": 14
|
|
},
|
|
"median_working_seconds": 137.2725,
|
|
"publishing_episodes": 4,
|
|
"peer_receiving_episodes": 2
|
|
},
|
|
"by_condition": {
|
|
"board": {
|
|
"episodes": 6,
|
|
"scorer_passes": 6,
|
|
"errors": 0,
|
|
"limits": 0,
|
|
"totals": {
|
|
"total_tokens": 1319153,
|
|
"input_tokens": 116083,
|
|
"cache_read_tokens": 1136321,
|
|
"cache_write_tokens": null,
|
|
"output_tokens": 66749,
|
|
"reasoning_tokens": 42952,
|
|
"working_seconds": 782.388,
|
|
"model_calls": 87,
|
|
"submit_tool_calls": 7
|
|
},
|
|
"median_working_seconds": 137.2725,
|
|
"publishing_episodes": 4,
|
|
"peer_receiving_episodes": 2
|
|
},
|
|
"private": {
|
|
"episodes": 6,
|
|
"scorer_passes": 6,
|
|
"errors": 0,
|
|
"limits": 0,
|
|
"totals": {
|
|
"total_tokens": 1049580,
|
|
"input_tokens": 124110,
|
|
"cache_read_tokens": 849427,
|
|
"cache_write_tokens": null,
|
|
"output_tokens": 76043,
|
|
"reasoning_tokens": 48694,
|
|
"working_seconds": 894.637,
|
|
"model_calls": 73,
|
|
"submit_tool_calls": 7
|
|
},
|
|
"median_working_seconds": 144.838,
|
|
"publishing_episodes": 0,
|
|
"peer_receiving_episodes": 0
|
|
}
|
|
},
|
|
"by_condition_split": {
|
|
"board/conflicting": {
|
|
"episodes": 4,
|
|
"scorer_passes": 4,
|
|
"errors": 0,
|
|
"limits": 0,
|
|
"totals": {
|
|
"total_tokens": 1259932,
|
|
"input_tokens": 102562,
|
|
"cache_read_tokens": 1095624,
|
|
"cache_write_tokens": null,
|
|
"output_tokens": 61746,
|
|
"reasoning_tokens": 40076,
|
|
"working_seconds": 717.075,
|
|
"model_calls": 76,
|
|
"submit_tool_calls": 5
|
|
},
|
|
"median_working_seconds": 175.34,
|
|
"publishing_episodes": 4,
|
|
"peer_receiving_episodes": 2
|
|
},
|
|
"board/original": {
|
|
"episodes": 2,
|
|
"scorer_passes": 2,
|
|
"errors": 0,
|
|
"limits": 0,
|
|
"totals": {
|
|
"total_tokens": 59221,
|
|
"input_tokens": 13521,
|
|
"cache_read_tokens": 40697,
|
|
"cache_write_tokens": null,
|
|
"output_tokens": 5003,
|
|
"reasoning_tokens": 2876,
|
|
"working_seconds": 65.313,
|
|
"model_calls": 11,
|
|
"submit_tool_calls": 2
|
|
},
|
|
"median_working_seconds": 32.6565,
|
|
"publishing_episodes": 0,
|
|
"peer_receiving_episodes": 0
|
|
},
|
|
"private/conflicting": {
|
|
"episodes": 4,
|
|
"scorer_passes": 4,
|
|
"errors": 0,
|
|
"limits": 0,
|
|
"totals": {
|
|
"total_tokens": 997206,
|
|
"input_tokens": 109463,
|
|
"cache_read_tokens": 818074,
|
|
"cache_write_tokens": null,
|
|
"output_tokens": 69669,
|
|
"reasoning_tokens": 44397,
|
|
"working_seconds": 811.954,
|
|
"model_calls": 63,
|
|
"submit_tool_calls": 5
|
|
},
|
|
"median_working_seconds": 187.2395,
|
|
"publishing_episodes": 0,
|
|
"peer_receiving_episodes": 0
|
|
},
|
|
"private/original": {
|
|
"episodes": 2,
|
|
"scorer_passes": 2,
|
|
"errors": 0,
|
|
"limits": 0,
|
|
"totals": {
|
|
"total_tokens": 52374,
|
|
"input_tokens": 14647,
|
|
"cache_read_tokens": 31353,
|
|
"cache_write_tokens": null,
|
|
"output_tokens": 6374,
|
|
"reasoning_tokens": 4297,
|
|
"working_seconds": 82.68299999999999,
|
|
"model_calls": 10,
|
|
"submit_tool_calls": 2
|
|
},
|
|
"median_working_seconds": 41.341499999999996,
|
|
"publishing_episodes": 0,
|
|
"peer_receiving_episodes": 0
|
|
}
|
|
},
|
|
"board_reading_episodes": 4,
|
|
"public_posts": 4,
|
|
"budget_before": {
|
|
"checked_at": "2026-09-07T21:17:38.880564+00:00",
|
|
"usage": 1.583748835,
|
|
"limit": 5,
|
|
"limit_remaining": 3.4162511650000003
|
|
},
|
|
"budget_after": {
|
|
"checked_at": "2026-09-07T21:32:53.404036+00:00",
|
|
"usage": 1.639910959,
|
|
"limit": 5,
|
|
"limit_remaining": 3.360089041,
|
|
"usage_delta": 0.05616212400000009
|
|
},
|
|
"limitations": [
|
|
"Scorer passes are not automatic behavioral labels.",
|
|
"Reasoning tokens are a subset of output, not an additional cost.",
|
|
"Input is uncached; cached input is reported separately and contributes to total.",
|
|
"Working seconds are summed episode time, not experiment wall time.",
|
|
"Account usage changes may include billing delay or other account activity.",
|
|
"Small dependent development-task samples; descriptive comparisons only."
|
|
]
|
|
}
|