Submission Reports
Select a report to view detailed benchmark data, charts, and run metrics.
| Submitter | System Name | Model | Precision | Framework | Division | Runs | Submitted | |
|---|---|---|---|---|---|---|---|---|
 | AMD | GPT-OSS 120B | mxfp4 OSL: 1300, ISL: 5011 | vLLM 0.6.5.dev964+mlperf50, Pytorch 2.7.0a0+git3a58512, ROCm 6.3.1 | Closed | 0 | 02/19/2026 | |
| AMD | GPT-OSS 120B | mxfp4 OSL: 1300, ISL: 5011 | PyTorch 2.9.1+git8907517, ROCm 7.0.0 | Closed | 0 | 02/19/2026 | |
 | QWEN3 CODER 480B | FP8 OSL: -1, ISL: -1 | vllm/vllm-tpu:nightly-ironwood-20260217-9d37d31-d00df62 | Open | 7 | 02/27/2026 | ||
| QWEN3 CODER 480B | FP8 OSL: -1, ISL: -1 | vllm/vllm-tpu:nightly-ironwood-20260217-9d37d31-d00df62 | Open | 8 | 02/27/2026 | ||
 | Intel | 1-node-4x-BMG-Pro-B60 1
Node | Llama-3.1-8B | INT4 OSL: 128, ISL: 870 | VLLM-0.11, vllm-xpu-kernels-0.0.1 | Closed | 11 | 02/27/2026 |
| Intel | 1-node-4x-BMG-B50 1
Node | Llama-3.1-8B | INT4 OSL: 128, ISL: 870 | VLLM-0.11, vllm-xpu-kernels-0.0.1 | Closed | 11 | 02/27/2026 |
 | Krai | HPE Cray XD670 1
Node | Llama-3.1-70B | BF16 OSL: 219, ISL: 222 | vLLM v0.16.0 | Closed | 10 | 02/27/2026 |
| Krai | HPE Cray XD670 1
Node | Llama-3.1-70B | BF16 OSL: 219, ISL: 222 | SGLang v0.5.9 | Closed | 10 | 02/27/2026 |
 | NVIDIA | Deepseek-R1 | FP4 OSL: 3886, ISL: 804 | TensorRT 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 | Closed | 10 | — | |
| NVIDIA | Deepseek-R1 | FP4 OSL: 3886, ISL: 804 | TensorRT 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 | Closed | 10 | — |