cmpatino's picture
download
raw
42.4 kB
{
"conditions": {
"solo-piv": {
"planned": 30,
"runs": 28,
"graded": 28,
"mean_reward": 0.22176165572783724,
"pct_resolved": 0.0,
"pct_almost": 0.0,
"mean_wall_s": 2077.9619882873126,
"mean_model_calls": 151.03571428571428,
"mean_tool_calls": 174.53571428571428,
"mean_prompt_tokens": 17619922.535714287,
"mean_completion_tokens": 137988.07142857142,
"mean_workers_used": null,
"mean_delegations": null,
"mean_reports": null,
"mean_worker_share": null,
"mean_format_errors": 0.03571428571428571,
"cpu_job_h": 16.348055555555554,
"serve_gpu_h_share_est": 3.486174209092367,
"submitted_by": {
"solo": 12,
"none": 16
}
},
"team-piv": {
"planned": 30,
"runs": 28,
"graded": 26,
"mean_reward": 0.2655542422174676,
"pct_resolved": 0.0,
"pct_almost": 0.0,
"mean_wall_s": 2758.717448915754,
"mean_model_calls": 158.42857142857142,
"mean_tool_calls": 403.17857142857144,
"mean_prompt_tokens": 17929135.35714286,
"mean_completion_tokens": 133954.75,
"mean_workers_used": 0,
"mean_delegations": 0,
"mean_reports": 0,
"mean_worker_share": 0.0,
"mean_format_errors": 0,
"cpu_job_h": 21.195833333333333,
"serve_gpu_h_share_est": 4.628270235352078,
"submitted_by": {
"lead": 15,
"none": 13
}
}
},
"paired": {
"n_tasks": 26,
"mean_diff": 0.03307864631624374,
"ci95": [
-0.03556701036712227,
0.1028406221226157
],
"team_better": 13,
"solo_better": 6,
"ties": 7,
"p_two_sided": 0.1670684814453125
},
"per_task": [
{
"task": "abishekvashok__cmatrix.5c082c6",
"difficulty": "easy",
"solo": 0.9466403162055336,
"team": 0.9486166007905138,
"diff": 0.0019762845849802257
},
{
"task": "anordal__shellharden.6a6ffd4",
"difficulty": "easy",
"solo": 0.3324200913242009,
"team": 0.4484018264840183,
"diff": 0.11598173515981736
},
{
"task": "arthursonzogni__json-tui.17a22b6",
"difficulty": "easy",
"solo": 0.42649006622516555,
"team": 0.5311258278145695,
"diff": 0.10463576158940396
},
{
"task": "cslarsen__jp2a.61d205f",
"difficulty": "easy",
"solo": 0.21711568938193343,
"team": 0.0,
"diff": -0.21711568938193343
},
{
"task": "kisielk__errcheck.dacab89",
"difficulty": "easy",
"solo": 0.5117647058823529,
"team": 0.40294117647058825,
"diff": -0.10882352941176465
},
{
"task": "multiprocessio__dsq.c3ae0ba",
"difficulty": "easy",
"solo": 0.5535055350553506,
"team": 0.507380073800738,
"diff": -0.04612546125461259
},
{
"task": "rbakbashev__elfcat.52f8cc7",
"difficulty": "easy",
"solo": 0.0,
"team": 0.0,
"diff": 0.0
},
{
"task": "sclevine__yj.8016400",
"difficulty": "easy",
"solo": 0.0,
"team": 0.0,
"diff": 0.0
},
{
"task": "sirwart__ripsecrets.34c9e03",
"difficulty": "easy",
"solo": 0.0,
"team": 0.4386252045826514,
"diff": 0.4386252045826514
},
{
"task": "wfxr__code-minimap.0ddeea5",
"difficulty": "easy",
"solo": 0.0,
"team": 0.0,
"diff": 0.0
},
{
"task": "brocode__fblog.3b54330",
"difficulty": "medium",
"solo": 0.0,
"team": 0.0,
"diff": 0.0
},
{
"task": "codesnap-rs__codesnap.f81e4f3",
"difficulty": "medium",
"solo": 0.46760070052539404,
"team": 0.23467600700525393,
"diff": -0.2329246935201401
},
{
"task": "ecumene__rust-sloth.051c559",
"difficulty": "medium",
"solo": 0.12105263157894737,
"team": 0.0,
"diff": -0.12105263157894737
},
{
"task": "facebook__zstd.1168da0",
"difficulty": "medium",
"solo": 0.0,
"team": 0.3228655544651619,
"diff": 0.3228655544651619
},
{
"task": "go-critic__go-critic.9aea378",
"difficulty": "medium",
"solo": 0.31237322515212984,
"team": 0.3488843813387424,
"diff": 0.03651115618661255
},
{
"task": "madler__pigz.fe4894f",
"difficulty": "medium",
"solo": 0.0,
"team": 0.40312876052948254,
"diff": 0.40312876052948254
},
{
"task": "nikolassv__bartib.6b9b5ce",
"difficulty": "medium",
"solo": 0.0,
"team": 0.0,
"diff": 0.0
},
{
"task": "ninja-build__ninja.cc60300",
"difficulty": "medium",
"solo": 0.0,
"team": 0.0,
"diff": 0.0
},
{
"task": "peco__peco.4e58dad",
"difficulty": "medium",
"solo": 0.6477366255144033,
"team": 0.6872427983539094,
"diff": 0.03950617283950619
},
{
"task": "sharkdp__fd.40d8eb3",
"difficulty": "medium",
"solo": 0.4,
"team": 0.0,
"diff": -0.4
},
{
"task": "canop__broot.d6c798e",
"difficulty": "hard",
"solo": 0.6078066914498141,
"team": 0.6282527881040892,
"diff": 0.020446096654275103
},
{
"task": "dandavison__delta.acd758f",
"difficulty": "hard",
"solo": 0.0,
"team": 0.0,
"diff": 0.0
},
{
"task": "doxygen__doxygen.966d98e",
"difficulty": "hard",
"solo": 0.18777292576419213,
"team": 0.24782608695652175,
"diff": 0.06005316119232962
},
{
"task": "jesseduffield__lazygit.1d0db51",
"difficulty": "hard",
"solo": 0.2549707602339181,
"team": 0.3824561403508772,
"diff": 0.1274853801169591
},
{
"task": "johnkerl__miller.8d85b46",
"difficulty": "hard",
"solo": 0.05711552913848466,
"team": 0.0625811300129808,
"diff": 0.005465600874496136
},
{
"task": "parcel-bundler__lightningcss.aa2ed1e",
"difficulty": "hard",
"solo": 0.0,
"team": 0.3094059405940594,
"diff": 0.3094059405940594
},
{
"task": "php__php-src.c891263",
"difficulty": "hard",
"solo": 0.0,
"team": null,
"diff": null
},
{
"task": "rvben__rumdl.2d75c4d",
"difficulty": "hard",
"solo": 0.1649608669476219,
"team": null,
"diff": null
},
{
"task": "skeema__skeema.6a76243",
"difficulty": "hard",
"solo": null,
"team": null,
"diff": null
},
{
"task": "typst__typst.88356d0",
"difficulty": "hard",
"solo": null,
"team": null,
"diff": null
}
],
"missing": [
{
"key": "team-piv__php__php-src.c891263__s0",
"status": "fetched",
"job_id": "6adaaa5b925af0e27d4f9009",
"why": "not graded"
},
{
"key": "team-piv__rvben__rumdl.2d75c4d__s0",
"status": "fetched",
"job_id": "6ada8c38925af0e27d4f7e11",
"why": "not graded"
},
{
"key": "solo-piv__skeema__skeema.6a76243__s0",
"status": "done",
"job_id": "6ada8d9f925af0e27d4f7ea1",
"why": "no run dir"
},
{
"key": "team-piv__skeema__skeema.6a76243__s0",
"status": "done",
"job_id": "6ada8e0a925af0e27d4f7ed8",
"why": "no run dir"
},
{
"key": "solo-piv__typst__typst.88356d0__s0",
"status": "done",
"job_id": "6ada8e77c191903149a76c13",
"why": "no run dir"
},
{
"key": "team-piv__typst__typst.88356d0__s0",
"status": "done",
"job_id": "6ada93bf925af0e27d4f8291",
"why": "no run dir"
}
],
"serve": {
"base_url": "https://6ada3417925af0e27d4f4e59--30000.hf.jobs/v1",
"checked_at": "2026-10-23T00:12:52Z",
"cost_usd": 40.5722,
"job_id": "6ada3417925af0e27d4f4e59",
"launched_at": "2026-10-22T16:05:25Z",
"ready": true,
"remaining_s": 13988,
"running_secs": 29212,
"served_model_name": "flint",
"stage": "RUNNING",
"timeout": "12h",
"url": "https://6ada3417925af0e27d4f4e59--30000.hf.jobs",
"gpu_h": 8.114444444444445
},
"runs": [
{
"run_id": "pb-solo-piv-abishekvashok--cmatrix.5c082c6__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.9466403162055336,
"passed": 479,
"total": 506,
"submitted": true,
"wall_s": 1040.257788181305,
"model_calls": 97,
"tool_calls": 107,
"prompt_tokens": 9660998,
"completion_tokens": 74641,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "abishekvashok__cmatrix.5c082c6",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.295
},
{
"run_id": "pb-team-piv-abishekvashok--cmatrix.5c082c6__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.9486166007905138,
"passed": 480,
"total": 506,
"submitted": true,
"wall_s": 2031.8017282485962,
"model_calls": 102,
"tool_calls": 115,
"prompt_tokens": 8864874,
"completion_tokens": 74642,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "abishekvashok__cmatrix.5c082c6",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.5708333333333333
},
{
"run_id": "pb-solo-piv-anordal--shellharden.6a6ffd4__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.3324200913242009,
"passed": 364,
"total": 1095,
"submitted": true,
"wall_s": 1725.9692385196686,
"model_calls": 130,
"tool_calls": 165,
"prompt_tokens": 13924594,
"completion_tokens": 123122,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "anordal__shellharden.6a6ffd4",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.4861111111111111
},
{
"run_id": "pb-team-piv-anordal--shellharden.6a6ffd4__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.4484018264840183,
"passed": 491,
"total": 1095,
"submitted": true,
"wall_s": 2020.9112622737885,
"model_calls": 111,
"tool_calls": 147,
"prompt_tokens": 10580821,
"completion_tokens": 141356,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "anordal__shellharden.6a6ffd4",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.5680555555555555
},
{
"run_id": "pb-solo-piv-arthursonzogni--json-tui.17a22b6__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.42649006622516555,
"passed": 322,
"total": 755,
"submitted": false,
"wall_s": 2773.358806848526,
"model_calls": 143,
"tool_calls": 157,
"prompt_tokens": 18177737,
"completion_tokens": 148906,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "arthursonzogni__json-tui.17a22b6",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.7761111111111111
},
{
"run_id": "pb-team-piv-arthursonzogni--json-tui.17a22b6__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.5311258278145695,
"passed": 401,
"total": 755,
"submitted": true,
"wall_s": 2522.8943254947662,
"model_calls": 163,
"tool_calls": 190,
"prompt_tokens": 19128945,
"completion_tokens": 108862,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "arthursonzogni__json-tui.17a22b6",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.7088888888888889
},
{
"run_id": "pb-solo-piv-cslarsen--jp2a.61d205f__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.21711568938193343,
"passed": 137,
"total": 631,
"submitted": false,
"wall_s": 2093.662011384964,
"model_calls": 146,
"tool_calls": 174,
"prompt_tokens": 17591319,
"completion_tokens": 159312,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "cslarsen__jp2a.61d205f",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.5883333333333334
},
{
"run_id": "pb-team-piv-cslarsen--jp2a.61d205f__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 631,
"submitted": false,
"wall_s": 2265.9727330207825,
"model_calls": 166,
"tool_calls": 675,
"prompt_tokens": 19824891,
"completion_tokens": 154743,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "cslarsen__jp2a.61d205f",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.6377777777777778
},
{
"run_id": "pb-solo-piv-kisielk--errcheck.dacab89__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.5117647058823529,
"passed": 174,
"total": 340,
"submitted": false,
"wall_s": 3151.274005174637,
"model_calls": 183,
"tool_calls": 219,
"prompt_tokens": 21911734,
"completion_tokens": 176991,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "kisielk__errcheck.dacab89",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.8813888888888889
},
{
"run_id": "pb-team-piv-kisielk--errcheck.dacab89__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.40294117647058825,
"passed": 137,
"total": 340,
"submitted": true,
"wall_s": 2871.615517139435,
"model_calls": 163,
"tool_calls": 190,
"prompt_tokens": 16905680,
"completion_tokens": 159861,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "kisielk__errcheck.dacab89",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.8052777777777778
},
{
"run_id": "pb-solo-piv-multiprocessio--dsq.c3ae0ba__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.5535055350553506,
"passed": 300,
"total": 542,
"submitted": true,
"wall_s": 1835.8480715751648,
"model_calls": 174,
"tool_calls": 217,
"prompt_tokens": 22593195,
"completion_tokens": 150484,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "multiprocessio__dsq.c3ae0ba",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.6325
},
{
"run_id": "pb-team-piv-multiprocessio--dsq.c3ae0ba__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.507380073800738,
"passed": 275,
"total": 542,
"submitted": true,
"wall_s": 2625.1290245056152,
"model_calls": 183,
"tool_calls": 230,
"prompt_tokens": 21812871,
"completion_tokens": 158556,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "multiprocessio__dsq.c3ae0ba",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.7352777777777778
},
{
"run_id": "pb-solo-piv-rbakbashev--elfcat.52f8cc7__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 564,
"submitted": false,
"wall_s": 1767.6165385246277,
"model_calls": 140,
"tool_calls": 149,
"prompt_tokens": 15762829,
"completion_tokens": 99686,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "rbakbashev__elfcat.52f8cc7",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.49833333333333335
},
{
"run_id": "pb-team-piv-rbakbashev--elfcat.52f8cc7__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 564,
"submitted": false,
"wall_s": 2208.8879964351654,
"model_calls": 122,
"tool_calls": 624,
"prompt_tokens": 12639155,
"completion_tokens": 122028,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "rbakbashev__elfcat.52f8cc7",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.6227777777777778
},
{
"run_id": "pb-solo-piv-sclevine--yj.8016400__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 767,
"submitted": false,
"wall_s": 2761.150712490082,
"model_calls": 174,
"tool_calls": 190,
"prompt_tokens": 23585319,
"completion_tokens": 165015,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "sclevine__yj.8016400",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.7730555555555556
},
{
"run_id": "pb-team-piv-sclevine--yj.8016400__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 767,
"submitted": false,
"wall_s": 3091.6292686462402,
"model_calls": 141,
"tool_calls": 644,
"prompt_tokens": 16793480,
"completion_tokens": 168961,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "sclevine__yj.8016400",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.8652777777777778
},
{
"run_id": "pb-solo-piv-sirwart--ripsecrets.34c9e03__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 611,
"submitted": false,
"wall_s": 2165.4423828125,
"model_calls": 151,
"tool_calls": 187,
"prompt_tokens": 14607456,
"completion_tokens": 150056,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "sirwart__ripsecrets.34c9e03",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.6086111111111111
},
{
"run_id": "pb-team-piv-sirwart--ripsecrets.34c9e03__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.4386252045826514,
"passed": 268,
"total": 611,
"submitted": true,
"wall_s": 2278.7690427303314,
"model_calls": 152,
"tool_calls": 180,
"prompt_tokens": 17089517,
"completion_tokens": 121288,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "sirwart__ripsecrets.34c9e03",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.6391666666666667
},
{
"run_id": "pb-solo-piv-wfxr--code-minimap.0ddeea5__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 313,
"submitted": false,
"wall_s": 2194.6198093891144,
"model_calls": 75,
"tool_calls": 89,
"prompt_tokens": 7684004,
"completion_tokens": 184927,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "wfxr__code-minimap.0ddeea5",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.43916666666666665
},
{
"run_id": "pb-team-piv-wfxr--code-minimap.0ddeea5__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 313,
"submitted": false,
"wall_s": 4598.91406083107,
"model_calls": 162,
"tool_calls": 658,
"prompt_tokens": 21240427,
"completion_tokens": 164072,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "wfxr__code-minimap.0ddeea5",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 1.2844444444444445
},
{
"run_id": "pb-solo-piv-brocode--fblog.3b54330__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 978,
"submitted": false,
"wall_s": 3105.7423453330994,
"model_calls": 116,
"tool_calls": 153,
"prompt_tokens": 15832113,
"completion_tokens": 151004,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "brocode__fblog.3b54330",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.8680555555555556
},
{
"run_id": "pb-team-piv-brocode--fblog.3b54330__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 978,
"submitted": false,
"wall_s": 2874.002379655838,
"model_calls": 124,
"tool_calls": 621,
"prompt_tokens": 15420952,
"completion_tokens": 145888,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "brocode__fblog.3b54330",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.8058333333333333
},
{
"run_id": "pb-solo-piv-codesnap-rs--codesnap.f81e4f3__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.46760070052539404,
"passed": 267,
"total": 571,
"submitted": true,
"wall_s": 2769.130465745926,
"model_calls": 212,
"tool_calls": 236,
"prompt_tokens": 24991966,
"completion_tokens": 136868,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "codesnap-rs__codesnap.f81e4f3",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.7747222222222222
},
{
"run_id": "pb-team-piv-codesnap-rs--codesnap.f81e4f3__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.23467600700525393,
"passed": 134,
"total": 571,
"submitted": true,
"wall_s": 1905.9554042816162,
"model_calls": 203,
"tool_calls": 241,
"prompt_tokens": 24815438,
"completion_tokens": 129641,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "codesnap-rs__codesnap.f81e4f3",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.05416666666666667
},
{
"run_id": "pb-solo-piv-ecumene--rust-sloth.051c559__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.12105263157894737,
"passed": 46,
"total": 380,
"submitted": true,
"wall_s": 1155.3648953437805,
"model_calls": 185,
"tool_calls": 202,
"prompt_tokens": 20960514,
"completion_tokens": 112351,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 1,
"submitted_by": "solo",
"task": "ecumene__rust-sloth.051c559",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.5363888888888889
},
{
"run_id": "pb-team-piv-ecumene--rust-sloth.051c559__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 380,
"submitted": false,
"wall_s": 3576.3658187389374,
"model_calls": 135,
"tool_calls": 628,
"prompt_tokens": 16561014,
"completion_tokens": 139797,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "ecumene__rust-sloth.051c559",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 1.0
},
{
"run_id": "pb-solo-piv-facebook--zstd.1168da0__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 2038,
"submitted": false,
"wall_s": 1966.0052092075348,
"model_calls": 157,
"tool_calls": 185,
"prompt_tokens": 17684534,
"completion_tokens": 151410,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "facebook__zstd.1168da0",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.395
},
{
"run_id": "pb-team-piv-facebook--zstd.1168da0__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.3228655544651619,
"passed": 658,
"total": 2038,
"submitted": true,
"wall_s": 1785.4197790622711,
"model_calls": 171,
"tool_calls": 201,
"prompt_tokens": 19735823,
"completion_tokens": 132833,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "facebook__zstd.1168da0",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.5058333333333334
},
{
"run_id": "pb-solo-piv-go-critic--go-critic.9aea378__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.31237322515212984,
"passed": 154,
"total": 493,
"submitted": true,
"wall_s": 1762.4964213371277,
"model_calls": 154,
"tool_calls": 183,
"prompt_tokens": 18258383,
"completion_tokens": 127525,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "go-critic__go-critic.9aea378",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.4963888888888889
},
{
"run_id": "pb-team-piv-go-critic--go-critic.9aea378__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.3488843813387424,
"passed": 172,
"total": 493,
"submitted": true,
"wall_s": 1884.3229551315308,
"model_calls": 149,
"tool_calls": 149,
"prompt_tokens": 13849024,
"completion_tokens": 116724,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "go-critic__go-critic.9aea378",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.5291666666666667
},
{
"run_id": "pb-solo-piv-madler--pigz.fe4894f__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 831,
"submitted": false,
"wall_s": 2521.9315526485443,
"model_calls": 181,
"tool_calls": 197,
"prompt_tokens": 23635505,
"completion_tokens": 163594,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "madler__pigz.fe4894f",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.7058333333333333
},
{
"run_id": "pb-team-piv-madler--pigz.fe4894f__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.40312876052948254,
"passed": 335,
"total": 831,
"submitted": true,
"wall_s": 2749.601504087448,
"model_calls": 176,
"tool_calls": 175,
"prompt_tokens": 16874039,
"completion_tokens": 157749,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "madler__pigz.fe4894f",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.7697222222222222
},
{
"run_id": "pb-solo-piv-nikolassv--bartib.6b9b5ce__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 721,
"submitted": false,
"wall_s": 2784.1649811267853,
"model_calls": 118,
"tool_calls": 120,
"prompt_tokens": 12244862,
"completion_tokens": 173535,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "nikolassv__bartib.6b9b5ce",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.7791666666666667
},
{
"run_id": "pb-team-piv-nikolassv--bartib.6b9b5ce__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 721,
"submitted": false,
"wall_s": 3688.141940832138,
"model_calls": 166,
"tool_calls": 666,
"prompt_tokens": 19934697,
"completion_tokens": 139876,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "nikolassv__bartib.6b9b5ce",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 1.0308333333333333
},
{
"run_id": "pb-solo-piv-ninja-build--ninja.cc60300__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 1438,
"submitted": false,
"wall_s": 2930.683688402176,
"model_calls": 126,
"tool_calls": 160,
"prompt_tokens": 15323234,
"completion_tokens": 162292,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "ninja-build__ninja.cc60300",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.8219444444444445
},
{
"run_id": "pb-team-piv-ninja-build--ninja.cc60300__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 1438,
"submitted": false,
"wall_s": 2567.462298154831,
"model_calls": 217,
"tool_calls": 696,
"prompt_tokens": 24924185,
"completion_tokens": 163778,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "ninja-build__ninja.cc60300",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.7213888888888889
},
{
"run_id": "pb-solo-piv-peco--peco.4e58dad__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.6477366255144033,
"passed": 787,
"total": 1215,
"submitted": true,
"wall_s": 2288.909306526184,
"model_calls": 140,
"tool_calls": 154,
"prompt_tokens": 15273369,
"completion_tokens": 117806,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "peco__peco.4e58dad",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.6541666666666667
},
{
"run_id": "pb-team-piv-peco--peco.4e58dad__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.6872427983539094,
"passed": 835,
"total": 1215,
"submitted": false,
"wall_s": 4230.13586807251,
"model_calls": 230,
"tool_calls": 722,
"prompt_tokens": 25664378,
"completion_tokens": 153712,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "peco__peco.4e58dad",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 1.1816666666666666
},
{
"run_id": "pb-solo-piv-sharkdp--fd.40d8eb3__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.4,
"passed": 494,
"total": 1235,
"submitted": false,
"wall_s": 1815.9232931137085,
"model_calls": 169,
"tool_calls": 202,
"prompt_tokens": 19113859,
"completion_tokens": 146437,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "sharkdp__fd.40d8eb3",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.5113888888888889
},
{
"run_id": "pb-team-piv-sharkdp--fd.40d8eb3__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 1235,
"submitted": false,
"wall_s": 6345.439287662506,
"model_calls": 166,
"tool_calls": 665,
"prompt_tokens": 22895885,
"completion_tokens": 145626,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "sharkdp__fd.40d8eb3",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 1.7686111111111111
},
{
"run_id": "pb-solo-piv-canop--broot.d6c798e__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.6078066914498141,
"passed": 327,
"total": 538,
"submitted": true,
"wall_s": 1449.1403226852417,
"model_calls": 119,
"tool_calls": 146,
"prompt_tokens": 14441561,
"completion_tokens": 105670,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "canop__broot.d6c798e",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.4102777777777778
},
{
"run_id": "pb-team-piv-canop--broot.d6c798e__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.6282527881040892,
"passed": 338,
"total": 538,
"submitted": true,
"wall_s": 1073.4909267425537,
"model_calls": 123,
"tool_calls": 140,
"prompt_tokens": 10827875,
"completion_tokens": 70062,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "canop__broot.d6c798e",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.305
},
{
"run_id": "pb-solo-piv-dandavison--delta.acd758f__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 949,
"submitted": false,
"wall_s": 1658.078307390213,
"model_calls": 185,
"tool_calls": 195,
"prompt_tokens": 24839072,
"completion_tokens": 116103,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "dandavison__delta.acd758f",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.4672222222222222
},
{
"run_id": "pb-team-piv-dandavison--delta.acd758f__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 949,
"submitted": false,
"wall_s": 3098.1821467876434,
"model_calls": 160,
"tool_calls": 662,
"prompt_tokens": 15823541,
"completion_tokens": 135829,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "dandavison__delta.acd758f",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.8669444444444444
},
{
"run_id": "pb-solo-piv-doxygen--doxygen.966d98e__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.18777292576419213,
"passed": 43,
"total": 229,
"submitted": true,
"wall_s": 1234.9721620082855,
"model_calls": 120,
"tool_calls": 183,
"prompt_tokens": 10349953,
"completion_tokens": 88103,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "doxygen__doxygen.966d98e",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.34944444444444445
},
{
"run_id": "pb-team-piv-doxygen--doxygen.966d98e__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.24782608695652175,
"passed": 57,
"total": 230,
"submitted": true,
"wall_s": 1140.7231023311615,
"model_calls": 105,
"tool_calls": 138,
"prompt_tokens": 8621801,
"completion_tokens": 89893,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "doxygen__doxygen.966d98e",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.32416666666666666
},
{
"run_id": "pb-solo-piv-jesseduffield--lazygit.1d0db51__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.2549707602339181,
"passed": 218,
"total": 855,
"submitted": true,
"wall_s": 1213.476420879364,
"model_calls": 120,
"tool_calls": 147,
"prompt_tokens": 10079768,
"completion_tokens": 87854,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "jesseduffield__lazygit.1d0db51",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.3427777777777778
},
{
"run_id": "pb-team-piv-jesseduffield--lazygit.1d0db51__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.3824561403508772,
"passed": 327,
"total": 855,
"submitted": true,
"wall_s": 808.958901643753,
"model_calls": 123,
"tool_calls": 123,
"prompt_tokens": 8966055,
"completion_tokens": 68516,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "jesseduffield__lazygit.1d0db51",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.23027777777777778
},
{
"run_id": "pb-solo-piv-johnkerl--miller.8d85b46__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.05711552913848466,
"passed": 836,
"total": 14637,
"submitted": true,
"wall_s": 1793.971554517746,
"model_calls": 215,
"tool_calls": 215,
"prompt_tokens": 25539343,
"completion_tokens": 150852,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "johnkerl__miller.8d85b46",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.5066666666666667
},
{
"run_id": "pb-team-piv-johnkerl--miller.8d85b46__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0625811300129808,
"passed": 916,
"total": 14637,
"submitted": false,
"wall_s": 2335.6315903663635,
"model_calls": 196,
"tool_calls": 714,
"prompt_tokens": 26703257,
"completion_tokens": 176168,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "johnkerl__miller.8d85b46",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.6566666666666666
},
{
"run_id": "pb-solo-piv-parcel-bundler--lightningcss.aa2ed1e__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 2828,
"submitted": false,
"wall_s": 2310.4260239601135,
"model_calls": 162,
"tool_calls": 161,
"prompt_tokens": 20192961,
"completion_tokens": 174411,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "parcel-bundler__lightningcss.aa2ed1e",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.6477777777777778
},
{
"run_id": "pb-team-piv-parcel-bundler--lightningcss.aa2ed1e__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.3094059405940594,
"passed": 875,
"total": 2828,
"submitted": true,
"wall_s": 1437.0546972751617,
"model_calls": 137,
"tool_calls": 169,
"prompt_tokens": 12171464,
"completion_tokens": 99822,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "parcel-bundler__lightningcss.aa2ed1e",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.405
},
{
"run_id": "pb-solo-piv-php--php-src.c891263__solo-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": true,
"reward": 0.0,
"passed": 0,
"total": 14288,
"submitted": false,
"wall_s": 1788.5137145519257,
"model_calls": 141,
"tool_calls": 172,
"prompt_tokens": 17321495,
"completion_tokens": 125747,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "none",
"task": "php__php-src.c891263",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.5033333333333333
},
{
"run_id": "pb-team-piv-php--php-src.c891263__team-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": false,
"reward": null,
"passed": null,
"total": null,
"submitted": true,
"wall_s": 2548.7379138469696,
"model_calls": 142,
"tool_calls": 162,
"prompt_tokens": 18512049,
"completion_tokens": 157720,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "lead",
"task": "php__php-src.c891263",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 0.7416666666666667
},
{
"run_id": "pb-solo-piv-rvben--rumdl.2d75c4d__solo-piv__s0",
"status": "ended",
"end_reason": "terminal",
"graded": true,
"reward": 0.1649608669476219,
"passed": 548,
"total": 3322,
"submitted": true,
"wall_s": 2124.8056423664093,
"model_calls": 196,
"tool_calls": 222,
"prompt_tokens": 21776154,
"completion_tokens": 138964,
"workers_used": null,
"delegations": null,
"reports": null,
"worker_share": null,
"format_errors": 0,
"submitted_by": "solo",
"task": "rvben__rumdl.2d75c4d",
"condition": "solo-piv",
"seed": 0,
"cpu_job_h": 0.5988888888888889
},
{
"run_id": "pb-team-piv-rvben--rumdl.2d75c4d__team-piv__s0",
"status": "ended",
"end_reason": "max_rounds",
"graded": false,
"reward": null,
"passed": null,
"total": null,
"submitted": false,
"wall_s": 6677.93709564209,
"model_calls": 248,
"tool_calls": 764,
"prompt_tokens": 34833652,
"completion_tokens": 152730,
"workers_used": 0,
"delegations": 0,
"reports": 0,
"worker_share": 0.0,
"format_errors": 0,
"submitted_by": "none",
"task": "rvben__rumdl.2d75c4d",
"condition": "team-piv",
"seed": 0,
"cpu_job_h": 1.8611111111111112
}
]
}

Xet Storage Details

Size:
42.4 kB
·
Xet hash:
62a30fa54ff932c2d7d0ed58f344d4b13b6d2f4f92c4a513dd2167b9cb125f14

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.