AMD Radeon Pro 5300M vs NVIDIA GeForce GTX 980 Comparison

The Verdict

The AMD Radeon Pro 5300M and NVIDIA GeForce GTX 980 are two end-of-life graphics processors that serve completely different purposes, and the recorded data makes that split obvious. The Radeon Pro 5300M wins only 2 of 10 head-to-head benchmarks, but those wins are decisive and in modern API workloads. The GeForce GTX 980 wins 8 of 10, with its advantages concentrated in legacy DirectX tests and raw compute through OpenCL.

The Radeon Pro 5300M is the pick for anyone running Metal-based applications or Vulkan workloads, where it leads by 121.8% and 23.8% respectively. Its 48th percentile ranking versus all GPUs, with an average benchmark score of 10013, places it slightly ahead of the GTX 980's 43rd percentile and 8167 average. The GTX 980, however, remains the stronger choice for DirectX 9 through 12 workloads and for general 3D rendering, where its Passmark G3D score of 11095 is nearly double the Radeon's 5918.

For a Mac user or someone targeting Apple-centric ecosystems, the Radeon Pro 5300M is the obvious choice. For a PC builder focused on DirectX gaming or OpenCL compute, the GTX 980 is the better performer. The data does not support a single universal winner, it supports two specialized tools.

Where Each One Wins

The Radeon Pro 5300M dominates in Apple-oriented and modern cross-platform APIs. Its Geekbench Metal score of 33626 crushes the GTX 980's 15163, a 121.8% advantage. In Geekbench Vulkan, it scores 27912 versus 22543, a 23.8% lead. These are the two benchmarks where the Navi 14 chip's RDNA 1.0 architecture shows its modern design.

The GeForce GTX 980 wins everywhere else. In Geekbench OpenCL, it scores 34676 against 29252, a 15.6% lead. The Passmark suite shows a clean sweep for NVIDIA. DirectX 10: 53 versus 36, a 32.1% advantage. DirectX 11: 83 versus 37, a 55.4% lead. DirectX 12: 46 versus 25, a 45.7% advantage. DirectX 9: 164 versus 80, a 51.2% lead. The 2D test goes to NVIDIA at 792 versus 582, a 26.5% margin. The G3D test shows 11095 versus 5918, a 46.7% edge. GPU compute via Passmark: 4753 versus 2658, a 44.1% lead.

The pattern is clear. The GTX 980 is a brute-force card that wins legacy API tests by wide margins, while the Radeon Pro 5300M is a modern mobile GPU that excels in Metal and Vulkan. The GTX 980's 2048 shading units, 128 TMUs, and 64 ROPs give it raw throughput advantages, but the Radeon's RDNA 1.0 architecture handles newer API calls more efficiently.

Architecture Differences

The two GPUs come from different eras and different design philosophies. The AMD Radeon Pro 5300M uses the Navi 14 chip built on RDNA 1.0 architecture, fabricated on TSMC's 7 nm process. It packs 6,400 million transistors into a 158 mm² die, yielding a transistor density of 40.5 million per square millimeter. The NVIDIA GeForce GTX 980 uses the GM204 chip on Maxwell 2.0 architecture, built on TSMC's 28 nm process. It holds 5,200 million transistors on a much larger 398 mm² die, with a density of just 13.1 million per square millimeter.

The memory subsystems differ substantially. The Radeon Pro 5300M uses 4 GB of GDDR6 on a 128-bit bus, delivering 192.0 GB/s bandwidth at 1500 MHz (12 Gbps effective). The GTX 980 uses 4 GB of GDDR5 on a 256-bit bus, delivering 224.4 GB/s bandwidth at 1753 MHz (7 Gbps effective). The GTX 980's wider bus gives it more bandwidth despite slower memory technology.

The compute resources tell a similar story. The Radeon Pro 5300M has 1280 shading units, 80 TMUs, and 32 ROPs. The GTX 980 has 2048 shading units, 128 TMUs, and 64 ROPs. The GTX 980's pixel rate of 77.82 GPixel/s and texture rate of 155.6 GTexel/s dwarf the Radeon's 40.00 GPixel/s and 100.0 GTexel/s. In FP32, the GTX 980 reaches 4.981 TFLOPS versus the Radeon's 3.200 TFLOPS. The Radeon does support FP16 at 6.400 TFLOPS (2:1 ratio), while the GTX 980 lists no FP16 capability.

Power and physical characteristics also diverge. The Radeon Pro 5300M draws 85 W with no power connectors, designed for portable devices with display output dependent on the host system. The GTX 980 draws 165 W, requires 2x 6-pin power connectors, a 450 W suggested PSU, and occupies a dual-slot 267 mm card. The Radeon uses PCIe 4.0 x8, while the GTX 980 uses PCIe 3.0 x16. Both support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 980 has no FP16 data, while the Radeon Pro 5300M includes it.

FAQ

Q: Which GPU is faster in Metal benchmarks?

A: The AMD Radeon Pro 5300M scores 33626 in Geekbench Metal, which is 121.8% higher than the NVIDIA GeForce GTX 980's 15163. This is the Radeon's largest winning margin in any test.

Q: Does the GeForce GTX 980 beat the Radeon Pro 5300M in DirectX tests?

A: Yes, the GTX 980 wins all four DirectX Passmark tests. The margins are 32.1% in DirectX 10, 55.4% in DirectX 11, 45.7% in DirectX 12, and 51.2% in DirectX 9.

Q: How do the two GPUs compare in overall average benchmark score?

A: The Radeon Pro 5300M has an average benchmark score of 10013, while the GTX 980 has 8167. The Radeon sits at the 48th percentile versus all GPUs, and the GTX 980 sits at the 43rd percentile.

Q: What are the memory differences between these cards?

A: Both have 4 GB of memory, but the Radeon Pro 5300M uses GDDR6 on a 128-bit bus with 192.0 GB/s bandwidth, while the GTX 980 uses GDDR5 on a 256-bit bus with 224.4 GB/s bandwidth.

Q: Which GPU is more power efficient?

A: The Radeon Pro 5300M has a TDP of 85 W with no power connectors, while the GTX 980 has a TDP of 165 W and requires 2x 6-pin power connectors plus a 450 W suggested PSU.

Q: What is the release timeline for these GPUs?

A: The GTX 980 was released on 2014-09-18, and the Radeon Pro 5300M was released on 2019-11-12. Both are end-of-life products.

Head-to-Head Benchmarks

The biggest win for the AMD Radeon Pro 5300M is in Geekbench Metal, where it scores 33626 against the GTX 980's 15163, a 121.8% difference. This is not a marginal victory, it is a complete demolition in Apple's graphics API. The Radeon also wins Geekbench Vulkan with 27912 versus 22543, a 23.8% lead. These two wins show that the RDNA 1.0 architecture is significantly better at handling modern, low-level APIs, likely due to its newer design and driver maturity in those areas.

The NVIDIA GeForce GTX 980 counters with a broad sweep across the remaining eight benchmarks. In Geekbench OpenCL, it scores 34676 versus 29252, a 15.6% lead, which is its narrowest winning margin. From there, the margins grow. Passmark DirectX 10 shows 53 versus 36, a 32.1% lead. DirectX 11 jumps to 83 versus 37, a 55.4% advantage. DirectX 12 shows 46 versus 25, a 45.7% lead. DirectX 9 is 164 versus 80, a 51.2% margin.

The 2D test, Passmark G2D, goes to NVIDIA at 792 versus 582, a 26.5% edge. The flagship G3D test shows 11095 versus 5918, a 46.7% lead. GPU compute via Passmark shows 4753 versus 2658, a 44.1% advantage. The GTX 980's wins are consistent and substantial, with most margins between 32% and 56%.

The data suggests that the GTX 980's larger shading unit count and wider memory bus give it a decisive edge in traditional rasterization and compute workloads. The Radeon Pro 5300M's wins indicate that its architecture is better optimized for Metal and Vulkan, which are the APIs that matter for modern macOS and Linux applications. The average benchmark scores reflect this split: the Radeon's 10013 average is 18.4% higher than the GTX 980's 8167, driven by the massive Metal score. The percentile rankings, 48th versus 43rd, show that the Radeon is slightly better positioned against the entire GPU landscape, but the GTX 980 remains competitive in its niche.

Specification Differences

The Radeon Pro 5300M and GTX 980 differ in nearly every hardware specification. The Radeon uses a 7 nm process from TSMC with 6,400 million transistors on a 158 mm² die, while the GTX 980 uses a 28 nm process from the same foundry with 5,200 million transistors on a 398 mm² die. The transistor densities are 40.5M per mm² versus 13.1M per mm².

Clock speeds differ slightly. The Radeon has a base clock of 1000 MHz and a boost of 1250 MHz. The GTX 980 has a base of 1127 MHz and a boost of 1216 MHz. Memory clocks are 1500 MHz (12 Gbps effective) for the Radeon and 1753 MHz (7 Gbps effective) for the GTX 980.

The memory configurations are similar in capacity but different in type and bus. Both have 4 GB, but the Radeon uses GDDR6 on a 128-bit bus with 192.0 GB/s bandwidth, while the GTX 980 uses GDDR5 on a 256-bit bus with 224.4 GB/s bandwidth.

Compute units differ significantly. The Radeon has 1280 shading units, 80 TMUs, and 32 ROPs. The GTX 980 has 2048 shading units, 128 TMUs, and 64 ROPs. Pixel rates are 40.00 GPixel/s versus 77.82 GPixel/s. Texture rates are 100.0 GTexel/s versus 155.6 GTexel/s. FP32 performance is 3.200 TFLOPS versus 4.981 TFLOPS. The Radeon supports FP16 at 6.400 TFLOPS, while the GTX 980 has no FP16 data.

Power and physical specs diverge completely. The Radeon draws 85 W with no power connectors and no specified slot width, designed for portable devices. The GTX 980 draws 165 W, requires 2x 6-pin power connectors, a 450 W suggested PSU, and is a dual-slot card measuring 267 mm in length, 111 mm in height, and 40 mm in width. Bus interfaces are PCIe 4.0 x8 for the Radeon and PCIe 3.0 x16 for the GTX 980. Display outputs are portable-device dependent for the Radeon, while the GTX 980 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2. The GTX 980 has a launch MSRP of 549 USD; the Radeon has no listed launch MSRP.