AMD Radeon 760M vs NVIDIA GeForce RTX 5090 SE Comparison

Where Each One Wins

The recorded data splits cleanly between the two parts. The AMD Radeon 760M is the only one with actual benchmark results in the database. It has ten recorded test scores covering DirectX 9, 10, 11, and 12, OpenCL, Vulkan, 2D graphics, 3D graphics, and compute workloads. Its average benchmark score sits at 6019, which places it at the 35th percentile of all GPUs in the database. The strongest result for the 760M comes from Geekbench Vulkan at 30336, while its weakest recorded result is Passmark DirectX 10 at just 19.

The NVIDIA GeForce RTX 5090 SE has no benchmark entries in the database at all. Its average benchmark score is recorded as zero, and there are no head-to-head benchmark comparisons between the two. This leaves the RTX 5090 SE without any measured performance data to analyze. The 760M therefore holds every recorded benchmark win by default, simply because it is the only one of the two with test scores on file.

Looking at the 760M's position among its nearest rivals, the data shows a tight cluster. The AMD Radeon RX 6400 scores 6001, which is 0.3% ahead of the 760M's average of 6019. The NVIDIA GeForce GTX 770M also sits at 6000, again 0.3% ahead. The NVIDIA RTX PRO 6000 Blackwell Server scores 5996, which is 0.4% ahead. The NVIDIA Quadro P2000 scores 6049, which puts it 0.5% behind the 760M. These deltas are all within a single percentage point, indicating that the 760M performs in a very narrow band around its nearest competition.

For the RTX 5090 SE, the absence of benchmarks means there is no recorded data on where it wins or loses. The database lists its percentile at 50 and its average score at zero, but without test results, no meaningful performance conclusions can be drawn from measurements.

Architecture Differences

The two GPUs come from different manufacturers, different architectures, and different market segments. The AMD Radeon 760M uses the Phoenix chip built on RDNA 3.0 architecture, described as Navi III IGP (Phoenix). It is manufactured by TSMC on a 4 nm process node. The chip contains 25,390 million transistors on a die size of 178 mm², giving a transistor density of 142.6 million transistors per mm². The RTX 5090 SE uses the GB202 chip built on Blackwell 2.0 architecture, part of the GeForce 50 series. It is also manufactured by TSMC but on a 5 nm process node. The GB202 die contains 92,200 million transistors on a 750 mm² die, giving a transistor density of 122.9 million transistors per mm².

The transistor counts differ substantially. The RTX 5090 SE's GB202 die has roughly 3.6 times the transistor count of the Phoenix chip, and its die is more than four times larger. However, the 760M actually has the higher transistor density at 142.6 million per mm² versus 122.9 million for the RTX 5090 SE, a consequence of the tighter 4 nm process.

The execution resources are far apart. The 760M has 512 shading units, 32 texture mapping units, 16 ROPs, and 8 ray tracing cores. The RTX 5090 SE has 14,080 shading units, 440 TMUs, 160 ROPs, 110 ray tracing cores, and 440 tensor cores. The RTX 5090 SE has no tensor cores listed for the 760M, which lacks dedicated AI acceleration hardware in the database record.

Clock behavior also differs. The 760M runs at a base clock of 800 MHz and boosts to 2599 MHz. The RTX 5090 SE has a base clock of 1740 MHz and a boost of 2377 MHz. The 760M has the higher boost clock, but the RTX 5090 SE starts from a much higher base.

Memory architecture is fundamentally different. The 760M uses system shared memory with a system shared bus width, system shared type, and system dependent bandwidth. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s of bandwidth, running at 1750 MHz or 28 Gbps effective.

Power and physical design are also far apart. The 760M is rated at 15 W TDP, uses no power connectors, is an IGP slot width, and has motherboard dependent display outputs. The RTX 5090 SE is rated at 500 W TDP, requires a single 16-pin power connector, a suggested 900 W power supply, is dual-slot, and measures 267 mm in length, 111 mm in height, and 40 mm in width. The bus interface differs as well: PCIe 4.0 x8 for the 760M versus PCIe 5.0 x16 for the RTX 5090 SE. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

FAQ

Q: Which GPU has the higher boost clock?

A: The AMD Radeon 760M boosts to 2599 MHz, while the NVIDIA GeForce RTX 5090 SE boosts to 2377 MHz.

Q: How much memory does the RTX 5090 SE have?

A: The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s of bandwidth.

Q: What is the TDP difference between the two?

A: The AMD Radeon 760M is rated at 15 W TDP, while the NVIDIA GeForce RTX 5090 SE is rated at 500 W TDP.

Q: Why does the RTX 5090 SE have no benchmark scores in the database?

A: The database record for the RTX 5090 SE contains an empty benchmarks array, resulting in an average benchmark score of zero and no head-to-head comparisons.

Q: What is the 760M's average benchmark score and percentile?

A: The AMD Radeon 760M has an average benchmark score of 6019 and sits at the 35th percentile of all GPUs in the database.

Q: Which GPU has more shading units?

A: The RTX 5090 SE has 14,080 shading units, compared to 512 for the AMD Radeon 760M.

Specification Differences

The two GPUs differ across nearly every recorded specification field. The 760M uses an AMD Phoenix chip on RDNA 3.0 architecture, while the RTX 5090 SE uses an NVIDIA GB202 chip on Blackwell 2.0 architecture. The process node is 4 nm for the 760M and 5 nm for the RTX 5090 SE, both from TSMC. Transistor count is 25,390 million for the 760M versus 92,200 million for the RTX 5090 SE. Die size is 178 mm² versus 750 mm². Transistor density is 142.6 million per mm² for the 760M versus 122.9 million per mm² for the RTX 5090 SE.

Base clocks are 800 MHz for the 760M and 1740 MHz for the RTX 5090 SE. Boost clocks are 2599 MHz versus 2377 MHz. Memory size is system shared versus 24 GB. Memory type is system shared versus GDDR7. Bus width is system shared versus 384 bit. Bandwidth is system dependent versus 1.34 TB/s. Shading units are 512 versus 14,080. TMUs are 32 versus 440. ROPs are 16 versus 160. Ray tracing cores are 8 versus 110. The RTX 5090 SE has 440 tensor cores; the 760M has none listed.

Pixel rate is 41.58 GPixel/s for the 760M versus 380.3 GPixel/s for the RTX 5090 SE. Texture rate is 83.17 GTexel/s versus 1,045.9 GTexel/s. FP32 performance is 5.323 TFLOPS versus 66.94 TFLOPS. FP16 is 5.323 TFLOPS (1:1) versus 66.94 TFLOPS (1:1). TDP is 15 W versus 500 W. Slot width is IGP versus dual-slot. Power connectors are none versus 1x 16-pin. Suggested PSU is not listed for the 760M versus 900 W for the RTX 5090 SE. Bus interface is PCIe 4.0 x8 versus PCIe 5.0 x16. Display outputs are motherboard dependent versus 1x HDMI 2.1b and 3x DisplayPort 2.1b. The RTX 5090 SE has dimensions of 267 mm length, 111 mm height, and 40 mm width; the 760M has no recorded dimensions.

Release dates differ: 2024-01-30 for the 760M and 2025-12-31 for the RTX 5090 SE. The 760M's predecessor is Navi II IGP, while the RTX 5090 SE's predecessor is GeForce 40. The RTX 5090 SE lists a successor of GeForce 60; the 760M has none. The launch MSRP for the RTX 5090 SE is 1,499 USD, while the 760M has no launch MSRP recorded.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries between the AMD Radeon 760M and the NVIDIA GeForce RTX 5090 SE. The headToHeadBenchmarks array is empty, and the wins counters for both parts are zero. This means there are no directly measured comparative results to walk through.

What can be examined is the 760M's standalone benchmark profile. Its Geekbench Vulkan score of 30336 is the highest single result in its record, followed by Geekbench OpenCL at 20255. The Passmark G3D score is 5310, Passmark G2D is 890, and Passmark GPU Compute is 2840. The DirectX tests are much lower: Passmark DirectX 9 scores 65, DirectX 11 scores 52, DirectX 12 scores 25, and DirectX 10 scores 19. These numbers show a wide gap between compute-oriented workloads and legacy DirectX tests for the 760M.

The 760M's nearest rival comparisons provide context for its average score. The AMD Radeon RX 6400 is 0.3% ahead, the NVIDIA GeForce GTX 770M is 0.3% ahead, the NVIDIA RTX PRO 6000 Blackwell Server is 0.4% ahead, and the NVIDIA Quadro P2000 is 0.5% behind. The 760M's average of 6019 places it within a narrow band around 6000, with all four nearest rivals within 0.5% either direction.

For the RTX 5090 SE, there is no benchmark data to analyze. Its percentile is listed at 50, which is higher than the 760M's 35th percentile, but its average score is zero due to the empty benchmarks array. Without recorded test results, the RTX 5090 SE cannot be compared to the 760M on any measured workload in the database. The only concrete comparisons available are architectural, such as the 760M's 5.323 TFLOPS FP32 performance versus the RTX 5090 SE's 66.94 TFLOPS, a roughly 12.6-fold difference in theoretical compute. The RTX 5090 SE also delivers 380.3 GPixel/s pixel rate versus 41.58 GPixel/s for the 760M, and 1,045.9 GTexel/s texture rate versus 83.17 GTexel/s. These are specification-based differences rather than measured benchmark results.