System Performance

MLPerf results measure a submitted model, system, hardware/software configuration and execution scenario. They are infrastructure performance observations, not a universal model quality score.

Preserve benchmark version, suite, scenario, units, accelerator count, submitter and source links when presenting a result. Filter by source-reported model, scenario, suite or performance unit. A throughput number from Offline is not interchangeable with a Server latency result.

On this page

List MLPerf system results

GET /api/v1/mlperf/results

Access: public read; no TensorTrace API key.

Parameters

NameLocationRequiredType / limitsMeaning
qqueryNostringCase-insensitive search text. Omit it to browse the complete matching catalog.
modelqueryNostringCase-insensitive substring of the source-reported model name.
scenarioqueryNostringCase-insensitive substring of the MLPerf execution scenario, such as Offline or Server.
unitqueryNostringBilling or performance unit, preserving the source’s explicit denominator. Compare only equivalent units.
suitequeryNostringCase-insensitive substring of the MLPerf suite label.
limitqueryNointeger Default: 50; Minimum: 1; Maximum: 200Maximum number of returned rows. The documented default and range apply; numeric pagination limits are clamped unless stated otherwise.
offsetqueryNointeger Default: 0; Minimum: 0Zero-based number of matching rows to skip. Default 0; negative values are clamped to 0.

Request example

curl 'https://tensortrace.net/api/v1/mlperf/results?limit=1'

Responses

StatusMeaningBody type
200Source-backed JSON responseSystemPerformanceResponse
400Invalid queryNo declared JSON body
404Unknown model/sourceNo declared JSON body
500Database unavailableNo declared JSON body
503Service temporarily unavailableNo declared JSON body

Response example · 200

Illustrative values; schema-valid and not a live catalog measurement.

{
    "data": [
        {
            "source_id": "mlperf",
            "source_record_id": "google/gemini-2.5-flash",
            "model_name": "Example submitted model",
            "updated_at": "2026-10-05T00:00:00Z",
            "canonical_model_id": "google/gemini-2.5-flash",
            "platform": "OpenRouter"
        }
    ],
    "total_count": 1
}
FieldTypeRequiredMeaning / constraints
dataarray of SystemPerformanceResultDtoYes
total_countintegerYes

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace