GeekRadar / The comparison desk
COMPARE.
Tested systems
CoreWeave

72 × NVIDIA GB200

Tested system

Processor
NVIDIA Grace (Neoverse-V2)
Graphics
NVIDIA GB200
Accelerator count
72
Nodes
18

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

72 × NVIDIA GB200

529,991* Tokens/s

Accuracy target / result
exact_match: 80.76572470373746 TOKENS_PER_SAMPLE: 3815.436645396536
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
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

72 × NVIDIA GB200

419,778* Tokens/s

Accuracy target / result
exact_match: 81.03919781221514 TOKENS_PER_SAMPLE: 3802.557201458523
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
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

72 × NVIDIA GB200

911,566* Tokens/s

Accuracy target / result
exact_match: 83.394
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
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

72 × NVIDIA GB200

901,058* Tokens/s

Accuracy target / result
exact_match: 83.424
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
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

72 × NVIDIA GB200

894,002* Tokens/s

Accuracy target / result
ROUGE1: 44.8296 ROUGE2: 22.4099 ROUGEL: 29.2105 TOKENS_PER_SAMPLE: 271.5
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
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

72 × NVIDIA GB200

910,621* Tokens/s

Accuracy target / result
ROUGE1: 44.8247 ROUGE2: 22.3971 ROUGEL: 29.2015 TOKENS_PER_SAMPLE: 271.7
Weight precision
fp4
Division
closed
System type
datacenter
Availability
available
Cores per processor
72
Processors per node
2
Nodes
18
Total accelerators
72
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
NVIDIA Grace (Neoverse-V2)
Graphics
NVIDIA GB200

Connectivity & software

Operating system
Ubuntu 24.04

System configuration

Reported host core count
72
Processors per node
2
Accelerator count
72
Nodes
18
Software stack
TensorRT-LLM feat/1.2-mlpinf, NVIDIA Dynamo mlperf-v6.0-dynamo-v0.8.0
Submission division
closed

* Provisional data