Nebius · Nebius B200 n1 (8x B200-SXM-180GB, TensorRT)
GPT-OSS-120B (MLPerf reference) · gpt-oss-120b · Interactive · run 01a00b4a-3870…
valid · Reported evidence
Measurements
output_token_throughput_tps · reported13,155.3 tokens_s
GPT-OSS-120B (MLPerf reference) · gpt-oss-120b · Interactive · interactive · 8× NVIDIA B200-SXM-180GB · mlperf_closed_99 · observed 2026-03-26
Identity
modelGPT-OSS-120B (MLPerf reference)
stackTensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentM
workloadgpt-oss-120b · Interactive
topology8× NVIDIA B200-SXM-180GB
harnessmlperf_loadgen v6.0
quality policymlperf_closed_99
comparison keysha256:7a327a252e8dc20e…
sha256:d19faafc77a828a6ef1df80…
Launch configuration
dtypefp4
notesB200 TGP 1000W
systemNebius B200 n1 (8x B200-SXM-180GB, TensorRT)
softwareTensorRT 10.14, CUDA 13.1, cuDNN 9.17, TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0, vLLM CentML:mlperf-inf-mm-q3vl-v6.0
availabilityavailable
Workload
namegpt-oss-120b · Interactive
streamingyes
load generationopen_loop
Canonical manifest
Show manifestHide manifest
{
"kind": "ServingRun",
"spec": {
"status": "valid",
"harness": {
"name": "mlperf_loadgen",
"version": "v6.0"
},
"topology": {
"nodeCount": 1,
"acceleratorModel": "NVIDIA B200-SXM-180GB",
"acceleratorVendor": "nvidia",
"acceleratorsPerNode": 8
},
"observedAt": "2026-03-26T19:39:54Z",
"modelDigest": "sha256:25d396066173182e38fe499acf87750416b561f71db6feef2907188a1d59dff7",
"measurements": [
{
"unit": "tokens_s",
"value": 13155.3,
"metric": "output_token_throughput_tps",
"statistic": "reported"
}
],
"sourceNative": {
"source": "mlperf-inference",
"metrics": {
"performance_units": "Tokens/s",
"performance_result": 13155.3
},
"category": "datacenter",
"division": "closed",
"scenario": "interactive",
"benchmark": "gpt-oss-120b",
"externalId": "v6.0/6.0-0083"
},
"qualityPolicy": "mlperf_closed_99",
"workloadDigest": "sha256:faf88e9537b8650b4eb9b378de3555b5bec98c2952321bceab5fd46bab7cb0e0",
"configurationDigest": "sha256:88adb2247f7ab7f0c78d1edd3718b651dcd306f0269c8f4e949e71764773038a"
},
"metadata": {
"name": "mlperf-v6-0-6-0-0083",
"title": "Nebius · gpt-oss-120b · Interactive",
"sourceRefs": [
{
"url": "https://github.com/mlcommons/submissions_inference_v6.0/tree/main/closed/Nebius/results/nebius_b200_n1"
}
]
},
"apiVersion": "kernelindex.dev/v1alpha1"
}Cite this result (permalink, digest, access date)
Report an issue with this serving run
MLPerf Inference · closed/datacenter · entry v6.0/6.0-0083 · shown unmodified as publishedAll serving results →JSON