8 × NVIDIA B200-SXM-180GB

Tested system

Processor: Intel(R) Xeon(R) Platinum 8562Y+
Graphics: NVIDIA B200-SXM-180GB
Accelerator count: 8
Nodes: 1

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

MLPerf Inference / deepseek-r1Offline · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

58,913.20^* Tokens/s

Accuracy target / result: exact_match: 80.9024612579763 TOKENS_PER_SAMPLE: 3888.048541476755
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 32
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Operating system: Ubuntu 24.04

MLPerf Inference / deepseek-r1Server · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

56,121.30^* Tokens/s

Accuracy target / result: exact_match: 81.60893345487693 TOKENS_PER_SAMPLE: 3816.3475387420235
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 32
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Operating system: Ubuntu 24.04

MLPerf Inference / gpt-oss-120bOffline · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

91,487.40^* Tokens/s

Accuracy target / result: exact_match: 83.901
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 32
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Operating system: Ubuntu 24.04

MLPerf Inference / gpt-oss-120bServer · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

90,204.70^* Tokens/s

Accuracy target / result: exact_match: 83.728
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 32
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Operating system: Ubuntu 24.04

MLPerf Inference / llama2-70b-99.9Offline · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

102,703^* Tokens/s

Accuracy target / result: ROUGE1: 44.833 ROUGE2: 22.4096 ROUGEL: 29.2097 TOKENS_PER_SAMPLE: 271.6
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 32
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Operating system: Ubuntu 24.04

MLPerf Inference / llama2-70b-99.9Server · v6.1 · Tokens/s

8 × NVIDIA B200-SXM-180GB

102,398^* Tokens/s

Accuracy target / result: ROUGE1: 44.8305 ROUGE2: 22.4096 ROUGEL: 29.21 TOKENS_PER_SAMPLE: 271.5
Weight precision: fp4
Division: closed
System type: datacenter
Availability: available
Cores per processor: 32
Processors per node: 2
Nodes: 1
Total accelerators: 8
Software stack: TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Operating system: Ubuntu 24.04

Processing & platform

Processor: Intel(R) Xeon(R) Platinum 8562Y+
Graphics: NVIDIA B200-SXM-180GB

Connectivity & software

Operating system: Ubuntu 24.04

System configuration

Reported host core count: 32
Processors per node: 2
Accelerator count: 8
Nodes: 1
Software stack: TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Submission division: closed

* Provisional data