NVIDIA B200 SXM6 vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results for the NVIDIA B200 SXM6 and the NVIDIA GeForce RTX 5090 Mobile. The B200 SXM6 has no recorded benchmark scores, while the RTX 5090 Mobile has a full suite of results. The absence of comparable measurements means the two GPUs cannot be ranked against each other through the usual benchmark comparison tools.

For the RTX 5090 Mobile, the recorded data shows an average benchmark score of 45,152, placing it in the 84th percentile of all GPUs in the database. Its nearest rivals in the database include the AMD Radeon Pro 5500 XT at 45,384 (0.5% higher), the Intel Arc A730M at 45,592 (1% higher), the NVIDIA RTX 5880 Ada Generation at 45,972 (1.8% higher), and the NVIDIA GeForce RTX 4070 Ti at 44,795 (0.8% lower). These deltas indicate the RTX 5090 Mobile sits in a tight performance cluster, with all four rivals within roughly 2% of its average score.

The B200 SXM6, by contrast, has no benchmark entries and an average benchmark score of zero. Its percentile rank of 50 reflects the lack of data rather than any measured performance. The database treats it as an active product with no validated test results, so any comparison must rely on the specification differences and architectural details recorded in the database.

Where Each One Wins

Without shared benchmark scores, the win analysis shifts to the recorded specifications and the RTX 5090 Mobile's measured results. In raw compute throughput, the B200 SXM6 shows 69.34 TFLOPS for FP32 and the same 69.34 TFLOPS for FP16 (1:1 ratio). The RTX 5090 Mobile delivers 31.80 TFLOPS for both FP32 and FP16, also at a 1:1 ratio. The B200 SXM6 therefore has roughly 2.18 times the FP32 throughput on paper, a substantial lead for dense compute workloads.

Memory capacity and bandwidth heavily favor the B200 SXM6. It carries 180 GB of HBM3e across an 8192-bit bus, yielding 8.19 TB/s of bandwidth. The RTX 5090 Mobile uses 24 GB of GDDR7 on a 256-bit bus, producing 896.0 GB/s. The B200 SXM6 has 7.5 times the memory capacity and about 9.1 times the bandwidth. For large model inference or data-intensive tasks, the B200 SXM6 has a decisive advantage.

The RTX 5090 Mobile counters in several areas. Its pixel rate of 169.7 GPixel/s far exceeds the B200 SXM6's 43.92 GPixel/s, a 3.86 times lead that matters for rasterization-heavy workloads. The RTX 5090 Mobile also has 112 ROPs versus 24 on the B200 SXM6, and it includes 82 dedicated RT cores, while the B200 SXM6 has no recorded RT core count. The RTX 5090 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4; the B200 SXM6 lists N/A for all three APIs, confirming its server-oriented design with no graphics output.

The RTX 5090 Mobile's measured benchmark results provide concrete wins in its own right. Its 3DMark Steel Nomad DX12 score of 5,871, Geekbench OpenCL score of 201,834, and Geekbench Vulkan score of 198,405 all come from the database. PassMark results show 30,034 for G3D, 13,401 for GPU compute, and lower scores for DirectX 9 (324), DirectX 10 (183), DirectX 11 (269), and DirectX 12 (138). The G2D score of 1,057 rounds out the picture.

FAQ

Q: Why does the B200 SXM6 have no benchmark scores in the database?

A: The database lists no benchmark entries for the B200 SXM6. Its average benchmark score is 0 and its percentile rank is 50, which reflects the absence of recorded test results rather than measured performance.

Q: What is the RTX 5090 Mobile's average benchmark score and percentile?

A: The RTX 5090 Mobile has an average benchmark score of 45,152 and sits in the 84th percentile of all GPUs in the database. Its closest rival is the AMD Radeon Pro 5500 XT with an average score of 45,384, just 0.5% higher.

Q: Which GPU has higher memory bandwidth?

A: The B200 SXM6 has 8.19 TB/s of bandwidth from its HBM3e memory on an 8192-bit bus. The RTX 5090 Mobile has 896.0 GB/s from GDDR7 on a 256-bit bus. The B200 SXM6 leads by roughly 9.1 times.

Q: Does the RTX 5090 Mobile support modern graphics APIs?

A: Yes. The RTX 5090 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The B200 SXM6 lists N/A for DirectX, OpenGL, and Vulkan, and has no display outputs.

Q: What are the transistor counts for each GPU?

A: The B200 SXM6 has 208,000 million transistors on a 1628 mm² die, giving a density of 127.8M per mm². The RTX 5090 Mobile has 45,600 million transistors on a 378 mm² die, with a density of 120.6M per mm². Both use a 5 nm process from TSMC.

Q: How do the power requirements compare?

A: The B200 SXM6 has a TDP of 1000 W with a suggested PSU of 1400 W, while the RTX 5090 Mobile has a TDP of 95 W and no suggested PSU listed. The B200 SXM6 uses an SXM module slot, and the RTX 5090 Mobile is an IGP with no power connectors.

Specification Differences

The two GPUs differ on nearly every recorded specification. The B200 SXM6 uses the GB100 chip, while the RTX 5090 Mobile uses GB203. The B200 SXM6 belongs to the Server Blackwell (Bxx) generation, and the RTX 5090 Mobile belongs to the GeForce 50 Mobile generation. The B200 SXM6 has no series designation, while the RTX 5090 Mobile is in the GeForce 50-series.

Clock speeds show a notable split. The B200 SXM6 has a base clock of 120 MHz and a boost clock of 1830 MHz. The RTX 5090 Mobile runs at a base of 990 MHz and a boost of 1515 MHz. Memory clocks also differ: the B200 SXM6 uses 2000 MHz (8 Gbps effective), and the RTX 5090 Mobile uses 1750 MHz (28 Gbps effective).

Memory configuration diverges sharply. The B200 SXM6 has 180 GB of HBM3e with an 8192-bit bus and 8.19 TB/s bandwidth. The RTX 5090 Mobile has 24 GB of GDDR7 with a 256-bit bus and 896.0 GB/s. The B200 SXM6 has 18,944 shading units, 592 TMUs, and 24 ROPs. The RTX 5090 Mobile has 10,496 shading units, 328 TMUs, and 112 ROPs. The B200 SXM6 has 592 tensor cores and no recorded RT cores; the RTX 5090 Mobile has 328 tensor cores and 82 RT cores.

Pixel and texture rates differ as well. The B200 SXM6 achieves 43.92 GPixel/s and 1,083.4 GTexel/s. The RTX 5090 Mobile achieves 169.7 GPixel/s and 496.9 GTexel/s. The B200 SXM6 has a TDP of 1000 W, while the RTX 5090 Mobile has a TDP of 95 W. The B200 SXM6 uses an SXM Module slot and a PCIe 6.0 x16 interface; the RTX 5090 Mobile is an IGP with PCIe 5.0 x16. The B200 SXM6 has no display outputs, and the RTX 5090 Mobile's outputs are listed as portable device dependent.

The B200 SXM6 supports no graphics APIs, while the RTX 5090 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The B200 SXM6 has a launch MSRP of 34,999 USD, and the RTX 5090 Mobile has no launch MSRP recorded. The B200 SXM6 released on 2024-10-31, and the RTX 5090 Mobile on 2025-03-26.

Architecture Differences

Both GPUs use a 5 nm TSMC process, but the underlying architectures differ. The B200 SXM6 uses the Blackwell architecture with the GB100 chip, while the RTX 5090 Mobile uses Blackwell 2.0 with the GB203 chip. The B200 SXM6's predecessor is listed as Server Hopper, and its successor as Server Rubin. The RTX 5090 Mobile's predecessor is GeForce 40 Mobile, with no successor listed.

Transistor density is close: the B200 SXM6 has 127.8M transistors per mm², and the RTX 5090 Mobile has 120.6M per mm². The die sizes differ substantially, with the B200 SXM6 at 1628 mm² and the RTX 5090 Mobile at 378 mm². The B200 SXM6's total transistor count of 208,000 million is more than 4.5 times the RTX 5090 Mobile's 45,600 million.

The B200 SXM6 uses HBM3e memory, which aligns with its server-class role, while the RTX 5090 Mobile uses GDDR7, a consumer-oriented memory type. The B200 SXM6 has no RT cores recorded, reflecting its compute-first design, while the RTX 5090 Mobile includes 82 RT cores for hardware ray tracing. The B200 SXM6 has 592 tensor cores, and the RTX 5090 Mobile has 328, indicating different AI acceleration capacities.

The B200 SXM6 has no display outputs and no graphics API support, which marks it as a pure accelerator. The RTX 5090 Mobile includes full graphics API support and portable device dependent outputs, making it suitable for laptop displays. The B200 SXM6 uses a PCIe 6.0 x16 interface, while the RTX 5090 Mobile uses PCIe 5.0 x16, a generation difference in bus technology.

The Verdict

The data presents two GPUs with fundamentally different purposes. The B200 SXM6 is a server accelerator with 180 GB of HBM3e, 8.19 TB/s of bandwidth, and 69.34 TFLOPS of FP32 compute. It has no graphics outputs, no API support, and a 1000 W TDP. The RTX 5090 Mobile is a laptop GPU with 24 GB of GDDR7, 896.0 GB/s of bandwidth, 31.80 TFLOPS, full DirectX 12 Ultimate support, and 82 RT cores at 95 W.

For compute-heavy server workloads, the B200 SXM6 has the clear specification lead. Its memory capacity and bandwidth dwarf the RTX 5090 Mobile, and its FP32 throughput is more than double. The absence of benchmark scores means the database cannot confirm real-world performance, but the recorded specifications point to a dominant position for large-scale parallel compute.

For graphics and ray tracing, the RTX 5090 Mobile has the advantage. Its 112 ROPs, 169.7 GPixel/s pixel rate, and dedicated RT cores support rasterization and ray-traced rendering. Its measured benchmark results, including the 3DMark Steel Nomad DX12 score of 5,871 and Geekbench OpenCL score of 201,834, confirm it operates in a competitive range near the RTX 4070 Ti, which scores 0.8% lower on average.

The database cannot produce a head-to-head winner because no shared benchmarks exist. Instead, the choice depends on workload: the B200 SXM6 for server-side compute and AI inference with massive memory, the RTX 5090 Mobile for portable graphics and gaming with modern API support. The B200 SXM6 carries a launch MSRP of 34,999 USD, while the RTX 5090 Mobile has no recorded launch price. Both remain active production status, but they serve separate markets entirely.