[
{
"id": "claude",
"name": "Claude Code + Sonnet 4.6",
"seconds": 254.36268067359924,
"normal_completion": false,
"termination": "費用予約枠で停止",
"passed": 20,
"tests": 20,
"calls": 16,
"input_tokens": 119936,
"output_tokens": 17761,
"estimated_yen": 92.05478099999999,
"uncertain_requests": 0,
"historical_all_trials_yen": 126.39104100000002,
"source_bytes": 22971,
"yen_per_passed_check": 4.602739049999999,
"full_pass_artifact_yen": 92.05478099999999
},
{
"id": "sente",
"name": "Sente + Sonnet 4.6",
"seconds": 236.02482104301453,
"normal_completion": false,
"termination": "API生成エラー",
"passed": 20,
"tests": 20,
"calls": 24,
"input_tokens": 89418,
"output_tokens": 14826,
"estimated_yen": 72.124668,
"uncertain_requests": 0,
"historical_all_trials_yen": 122.69766600000001,
"source_bytes": 25898,
"yen_per_passed_check": 3.6062334,
"full_pass_artifact_yen": 72.124668
},
{
"id": "opencode",
"name": "OpenCode + Sonnet 4.6",
"seconds": 295.25546002388,
"normal_completion": false,
"termination": "費用予約枠で停止",
"passed": 20,
"tests": 20,
"calls": 22,
"input_tokens": 105757,
"output_tokens": 19513,
"estimated_yen": 89.665002,
"uncertain_requests": 0,
"historical_all_trials_yen": 139.915629,
"source_bytes": 19085,
"yen_per_passed_check": 4.4832501,
"full_pass_artifact_yen": 89.665002
},
{
"id": "glm",
"name": "Sente + GLM-5.3 Flash",
"seconds": 196.1184549331665,
"normal_completion": false,
"termination": "API生成エラー",
"passed": 3,
"tests": 20,
"calls": 2,
"input_tokens": 5934,
"output_tokens": 3010,
"estimated_yen": 0.15101980950000002,
"uncertain_requests": 1,
"historical_all_trials_yen": 0.15101980950000002,
"source_bytes": 9787,
"yen_per_passed_check": 0.05033993650000001,
"full_pass_artifact_yen": null
},
{
"id": "hy4",
"name": "Sente + HY4 Preview",
"seconds": 279.56500601768494,
"normal_completion": true,
"termination": "正常終了",
"passed": 20,
"tests": 20,
"calls": 23,
"input_tokens": 83601,
"output_tokens": 16381,
"estimated_yen": 16.271740904999998,
"uncertain_requests": 0,
"historical_all_trials_yen": 16.271740904999998,
"source_bytes": 20621,
"yen_per_passed_check": 0.8135870452499999,
"full_pass_artifact_yen": 16.271740904999998
},
{
"id": "glm52",
"name": "Sente + GLM-5.2",
"seconds": 39.35099411010742,
"normal_completion": true,
"termination": "正常終了",
"passed": 20,
"tests": 20,
"calls": 7,
"input_tokens": 22839,
"output_tokens": 6756,
"estimated_yen": 2.1359035169999996,
"uncertain_requests": 0,
"historical_all_trials_yen": 2.1359035169999996,
"source_bytes": 17531,
"failed_tests": []
},
{
"id": "k3",
"name": "Sente + Kimi K3",
"seconds": 41.90900111198425,
"normal_completion": true,
"termination": "正常終了",
"passed": 17,
"tests": 20,
"calls": 5,
"input_tokens": 15543,
"output_tokens": 5913,
"estimated_yen": 17.596011485308477,
"uncertain_requests": 0,
"historical_all_trials_yen": 17.596011485308477,
"source_bytes": 15302,
"failed_tests": [
{
"name": "01 loads empty with no runtime error",
"pass": false,
"error": "Cannot set properties of null (setting 'textContent'); Cannot set properties of null (setting 'textContent')",
"ms": 605
},
{
"name": "13 global counts correct",
"pass": false,
"error": "total wrong",
"ms": 149
},
{
"name": "15 invalid saved JSON recoverable",
"pass": false,
"error": "runtime exception on invalid JSON",
"ms": 107
}
]
},
{
"id": "fable",
"name": "Sente + Fable 5.1",
"seconds": 126.0208969116211,
"normal_completion": false,
"termination": "費用予約枠で停止",
"passed": 20,
"tests": 20,
"calls": 8,
"input_tokens": 23936,
"output_tokens": 9961,
"estimated_yen": 108.39927,
"uncertain_requests": 0,
"historical_all_trials_yen": 108.39927,
"source_bytes": 19912,
"failed_tests": []
},
{
"id": "haiku",
"name": "Sente + Haiku 4.5",
"seconds": 142.35962915420532,
"normal_completion": true,
"termination": "正常終了",
"passed": 3,
"tests": 20,
"calls": 23,
"input_tokens": 114824,
"output_tokens": 13306,
"estimated_yen": 26.659038,
"uncertain_requests": 0,
"historical_all_trials_yen": 26.659038,
"source_bytes": 19198,
"failed_tests": [
{
"name": "01 loads empty with no runtime error",
"pass": false,
"error": "missing empty state",
"ms": 1232
},
{
"name": "02 create title/notes/priority/due",
"pass": false,
"error": "creation failed",
"ms": 139
},
{
"name": "04 edit title persists",
"pass": false,
"error": "locator.click: Timeout 3500ms exceeded.\nCall log:\n \u001b[2m- waiting for getByTestId('task-item').filter({ hasText: 'Original' }).getByTestId('task-edit')\u001b[22m\n",
"ms": 3560
},
{
"name": "05 completion toggle reversible and persisted",
"pass": false,
"error": "locator.check: Timeout 3500ms exceeded.\nCall log:\n \u001b[2m- waiting for getByTestId('task-item').filter({ hasText: 'Toggle me' }).getByTestId('task-toggle')\u001b[22m\n",
"ms": 3601
},
{
"name": "06 deletion persists",
"pass": false,
"error": "locator.click: Timeout 3500ms exceeded.\nCall log:\n \u001b[2m- waiting for getByTestId('task-item').filter({ hasText: 'Delete me' }).getByTestId('task-delete')\u001b[22m\n",
"ms": 3582
},
{
"name": "07 case-insensitive title search",
"pass": false,
"error": "title search failed",
"ms": 172
},
{
"name": "08 case-insensitive notes search",
"pass": false,
"error": "notes search failed",
"ms": 168
},
{
"name": "09 status filter active/completed/all",
"pass": false,
"error": "locator.check: Timeout 3500ms exceeded.\nCall log:\n \u001b[2m- waiting for getByTestId('task-item').filter({ hasText: 'Alpha release' }).getByTestId('task-toggle')\u001b[22m\n",
"ms": 3660
},
{
"name": "10 priority filter",
"pass": false,
"error": "priority filter failed",
"ms": 172
},
{
"name": "11 filters and search compose",
"pass": false,
"error": "locator.check: Timeout 3500ms exceeded.\nCall log:\n \u001b[2m- waiting for getByTestId('task-item').filter({ hasText: 'Alpha release' }).getByTestId('task-toggle')\u001b[22m\n",
"ms": 3661
},
{
"name": "12 empty search state visible",
"pass": false,
"error": "no empty search state",
"ms": 174
},
{
"name": "13 global counts correct",
"pass": false,
"error": "locator.check: Timeout 3500ms exceeded.\nCall log:\n \u001b[2m- waiting for getByTestId('task-item').filter({ hasText: 'Alpha release' }).getByTestId('task-toggle')\u001b[22m\n",
"ms": 3660
},
{
"name": "14 multiple tasks survive reload",
"pass": false,
"error": "tasks lost on reload",
"ms": 175
},
{
"name": "15 invalid saved JSON recoverable",
"pass": false,
"error": "no task storage key",
"ms": 60
},
{
"name": "16 title and notes HTML injection prevented",
"pass": false,
"error": "task missing",
"ms": 219
},
{
"name": "18 mobile no overflow and form usable",
"pass": false,
"error": "mobile form not usable",
"ms": 732
},
{
"name": "19 inputs have accessible labels",
"pass": false,
"error": "[\"\",\"\",\"