Run: run_mastra_pm_001
VERIFIED
SystemMastra
BenchmarkPersonaMem
Harnessv0.9.4
Verified Overall81.5%
Nuance Overall74.9%
DateMay 3, 2026
run_manifest.jsonjson
{
"version": "1.0.0",
"runId": "run_mastra_pm_001",
"systemId": "sys_mastra",
"systemName": "Mastra",
"benchmarkId": "bench_personamem",
"benchmarkName": "PersonaMem",
"benchmarkVersion": "2.0",
"harnessVersion": "0.9.4",
"judgeModel": "gpt-4o-2025-03-26",
"judgeTemperature": 0,
"startedAt": "2026-05-03T20:30:00Z",
"completedAt": "2026-05-03T22:11:07Z",
"scores": {
"verified": {
"recall": 83.7,
"temporal": 78.2,
"reasoning": 82.1,
"overall": 81.5
},
"nuance": {
"recall": 77.1,
"temporal": 71.8,
"reasoning": 75.4,
"overall": 74.9
}
},
"questionCount": 200,
"passCount": 158,
"failCount": 42,
"merkleRoot": "4d5e6f7a8b9c0d1e2f3a4b5c6d7e8f9a0b1c2d3e4f5a6b7c8d9e0f1a2b3c4d5e"
}