Run: run_5f8cac732bcf
VERIFIED
Systemmem0-local
BenchmarkLongMemEval
Harnessv0.1.0
Verified Overall0%
Nuance Overall33.14333771999676%
DateMay 11, 2026
run_manifest.jsonjson
{
"version": "1.0.0",
"runId": "run_5f8cac732bcf",
"systemId": "sys_mem0-local",
"systemName": "mem0-local",
"benchmarkId": "bench_longmemeval-v1",
"benchmarkName": "LongMemEval",
"benchmarkVersion": "1.0",
"harnessVersion": "0.1.0",
"judgeModel": "openai/gpt-4o-mini",
"judgeTemperature": 0,
"startedAt": "2026-05-11T21:08:54.626661+00:00",
"completedAt": "2026-05-11T22:18:51.726560+00:00",
"scores": {
"verified": {
"recall": 0,
"temporal": 0,
"reasoning": 0,
"overall": 0
},
"nuance": {
"recall": 47.43589743589743,
"temporal": 36.95652173913043,
"reasoning": 15.037593984962406,
"overall": 33.14333771999676
}
},
"questionCount": 500,
"passCount": 162,
"failCount": 338,
"merkleRoot": "c4879d6f9dd98984bf1d982339c01b3c005b20f127d20a418800ebd492be93e7"
}