Compare · GPUs & AI chips

Blackwell B200 SXM vs TPU v5p

RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP #3 VS #13 CHECKED 06 SEPT 2026

Side by side

Verdict

Blackwell B200 SXM ranks #3 of 20 on Dense FP16/BF16 tensor TFLOPS per chip (2.25 PFLOPS); TPU v5p ranks #13 (459 TFLOPS).

Rank 03 of 20 · leads

Blackwell B200 SXM

Dense FP16/BF16 tensor TFLOPS per chip

2.25 PFLOPS

MakerNVIDIA

Date2025

Verified04 Sept 2026

Evidence

NVIDIA HGX Platform page, HGX B200 row ("8x NVIDIA Blackwell SXM", footnote 4: "HGX B300 and HGX B200 shipping now"). FP16/BF16 Tensor Core is listed as 36 PFLOPS for the 8-GPU board. Footnote 2: dense is half the sparse spec. Dense board total is therefore 18 PFLOPS; per chip 18 / 8 = 2.25 PFLOPS. Total memory 1.4 TB => 180 GB HBM3E per SXM.

Rank 13 of 20

TPU v5p

Dense FP16/BF16 tensor TFLOPS per chip

459 TFLOPS

MakerGoogle

Date2023

Verified04 Sept 2026

Evidence

Google Cloud TPU v5p documentation, per-chip specification table: "Peak compute per chip (BF16) (TFLOPs) 459". Same page lists FP8 at 459 TFLOPs. 95 GiB HBM per chip.

Try another pair

More Blackwell B200 SXM matchups

Source Vendor product pages and official spec documents (AMD Instinct MI355X / MI350X / MI325X / MI300X / MI300A / MI250X / MI250 / MI210; NVIDIA… Last checked 06 Sept 2026

Full GPUs & AI chips ranking Spot an error? Send a tip