Compare · GPUs & AI chips

Blackwell Ultra B300 SXM vs H100 SXM

RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP #4 VS #9 CHECKED 06 SEPT 2026

Side by side

Verdict

Blackwell Ultra B300 SXM ranks #4 of 20 on Dense FP16/BF16 tensor TFLOPS per chip (2.25 PFLOPS); H100 SXM ranks #9 (0.990 PFLOPS).

Rank 04 of 20 · leads

Blackwell Ultra B300 SXM

Dense FP16/BF16 tensor TFLOPS per chip

2.25 PFLOPS

MakerNVIDIA

Date2025

Verified04 Sept 2026

Evidence

NVIDIA HGX Platform page, HGX B300 row ("8x NVIDIA Blackwell Ultra SXM", shipping now). FP16/BF16 Tensor Core is the same 36 PFLOPS sparse / 18 PFLOPS dense board total as B200, so 2.25 PFLOPS dense per chip. B300's advertised uplift versus B200 is at FP4 and HBM capacity, not at dense FP16/BF16 — so on this metric B200 and B300 are tied.

Rank 09 of 20

H100 SXM

Dense FP16/BF16 tensor TFLOPS per chip

0.990 PFLOPS

MakerNVIDIA

Date2022

Verified04 Sept 2026

Evidence

NVIDIA H100 product page, H100 SXM column: FP16/BF16 Tensor Core 1,979 teraFLOPS. H100 datasheet footnote 2: "With sparsity." Dense is 1,979 / 2 = 989.5 TFLOPS (0.990 PFLOPS). 80 GB HBM3. Tied with H200 SXM on this compute metric.

Try another pair

More Blackwell Ultra B300 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