Compare · GPUs & AI chips
Blackwell Ultra B300 SXM vs A100 SXM 80GB
RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP
#4 VS #17
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); A100 SXM 80GB ranks #17 (312 TFLOPS).
Rank 04 of 20 · leads
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 17 of 20
Dense FP16/BF16 tensor TFLOPS per chip
312 TFLOPS
MakerNVIDIA
Date2020
Verified04 Sept 2026
Evidence
NVIDIA A100 product page, A100 80GB SXM column: FP16 Tensor Core 312 TFLOPS | 624 TFLOPS* and BFLOAT16 Tensor Core 312 TFLOPS | 624 TFLOPS*. Asterisk is "With sparsity". Dense figure used here is 312 TFLOPS. 80 GB HBM2e.Try another pair
More Blackwell Ultra B300 SXM matchups
- Blackwell Ultra B300 SXM vs Instinct MI355X
- Blackwell Ultra B300 SXM vs Instinct MI350X
- Blackwell Ultra B300 SXM vs Blackwell B200 SXM
- Blackwell Ultra B300 SXM vs Gaudi 3
- Blackwell Ultra B300 SXM vs Instinct MI325X
- Blackwell Ultra B300 SXM vs Instinct MI300X
- Blackwell Ultra B300 SXM vs H200 SXM
- Blackwell Ultra B300 SXM vs H100 SXM
- Blackwell Ultra B300 SXM vs Instinct MI300A
- Blackwell Ultra B300 SXM vs TPU v6e (Trillium)
- Blackwell Ultra B300 SXM vs Trainium2
- Blackwell Ultra B300 SXM vs TPU v5p
Source Vendor product pages and official spec documents (AMD Instinct MI355X / MI350X / MI325X / MI300X / MI300A / MI250X / MI250 / MI210; NVIDIA…
Last checked 06 Sept 2026