AMD Radeon R7 M370 vs NVIDIA GeForce GTX 980 Comparison

FAQ

Q: How does the NVIDIA GeForce GTX 980 compare to the AMD Radeon R7 M370 in average benchmark score?

A: The GTX 980 records an average benchmark score of 8167, placing it in the 43rd percentile of all GPUs. The R7 M370 scores 6764 on average, sitting in the 38th percentile. The GTX 980 is roughly 21% higher in aggregate score.

Q: Which card wins in OpenCL compute performance?

A: The GTX 980 dominates, scoring 34676 in Geekbench OpenCL versus 7063 for the R7 M370. That is a 391% advantage, the largest single-test gap in the head-to-head data.

Q: What about Vulkan performance?

A: The GTX 980 scores 22543 in Geekbench Vulkan compared to 6465 for the R7 M370. The NVIDIA card leads by 248.7%, a substantial margin but smaller than its OpenCL lead.

Q: Which GPU has the higher transistor density?

A: The GTX 980, built on TSMC's 28 nm process, packs 5,200 million transistors into a 398 mm² die for a density of 13.1M per mm². The R7 M370 uses the same 28 nm node but fits 950 million transistors into 77 mm², yielding 12.3M per mm².

Q: What are the nearest rivals for each card?

A: The GTX 980's closest competitor is the NVIDIA GeForce GTX 950M, just 0.4% behind in average score. The R7 M370's nearest rival is the AMD FirePro M5100, which is 1% ahead. The FirePro M5100 actually out-scores the R7 M370.

Q: Which card supports a higher DirectX feature level?

A: The GTX 980 supports DirectX 12 (12_1), while the R7 M370 supports DirectX 12 (11_1). The NVIDIA GPU also lists Vulkan 1.4 support versus Vulkan 1.2.170 on the AMD part.

Architecture Differences

The NVIDIA GeForce GTX 980 and AMD Radeon R7 M370 come from fundamentally different design philosophies. The GTX 980 uses NVIDIA's Maxwell 2.0 architecture on the GM204 chip, while the R7 M370 relies on AMD's GCN 1.0 architecture on the Litho chip. Both are fabricated by TSMC on the same 28 nm process, but that is where the similarities end.

The silicon scale difference is enormous. The GTX 980 integrates 5,200 million transistors across a 398 mm² die, producing a transistor density of 13.1M per mm². The R7 M370 contains only 950 million transistors on a 77 mm² die, with a density of 12.3M per mm². In absolute terms, the GTX 980 has roughly 5.5 times the transistor count and a die over five times larger.

The execution resources reflect that gap. The GTX 980 packs 2048 shading units, 128 texture mapping units, and 64 ROPs. The R7 M370 offers 384 shading units, 24 TMUs, and just 8 ROPs. That translates to a pixel rate of 77.82 GPixel/s and a texture rate of 155.6 GTexel/s for the GTX 980, versus 7.680 GPixel/s and 23.04 GTexel/s for the R7 M370. The FP32 compute throughput tells the same story: 4.981 TFLOPS for the NVIDIA card versus 737.3 GFLOPS for the AMD part.

Clock behavior also differs. The GTX 980 runs at a 1127 MHz base clock with a 1216 MHz boost. The R7 M370 operates at 875 MHz base and 960 MHz boost. Memory clocks diverge sharply as well: the GTX 980 uses 1753 MHz (7 Gbps effective) GDDR5, while the R7 M370 runs 900 MHz (3.6 Gbps effective) GDDR5.

The memory subsystem is a major architectural differentiator. The GTX 980 has 4 GB of GDDR5 on a 256-bit bus, delivering 224.4 GB/s of bandwidth. The R7 M370 has 2 GB of GDDR5 on a 128-bit bus, yielding just 57.60 GB/s. That is nearly a 4x bandwidth advantage for the NVIDIA card.

Interface and API support differ too. The GTX 980 uses PCIe 3.0 x16, while the R7 M370 uses PCIe 3.0 x8. The GTX 980 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The R7 M370 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The NVIDIA card also has a defined dual-slot cooler, dual 6-pin power connectors, a 450 W suggested PSU, and a 267 mm length, while the AMD card has no recorded dimensions, power connectors, or TDP in the database.

The GTX 980 was released on 2014-09-18 with a launch MSRP of 549 USD. The R7 M370 followed on 2015-05-04 with no recorded launch MSRP. Both are marked end-of-life. The GTX 980's predecessor is GeForce 700 and its successor is GeForce 10; the R7 M370's predecessor is Solar System and its successor is Polaris Mobile.

Head-to-Head Benchmarks

The database contains two directly comparable benchmark results for these GPUs, and the GTX 980 wins both decisively.

In Geekbench OpenCL, the GTX 980 scores 34676 against 7063 for the R7 M370. The delta is 391%, meaning the NVIDIA card delivers nearly five times the compute throughput in this test. This result aligns with the raw FP32 figures: 4.981 TFLOPS versus 737.3 GFLOPS. OpenCL workloads that scale with shading units and memory bandwidth will heavily favor the GTX 980, and the recorded data confirms it.

Geekbench Vulkan narrows the gap somewhat but still favors NVIDIA heavily. The GTX 980 scores 22543 versus 6465 for the R7 M370, a 248.7% lead. Vulkan performance depends on driver efficiency and API feature level, and the GTX 980's Vulkan 1.4 support versus 1.2.170 on the AMD card likely contributes to the margin. Still, the raw hardware advantage of the GTX 980, with 2048 shading units and 224.4 GB/s of bandwidth, makes the outcome unsurprising.

The GTX 980 also holds a clear edge in the overall average benchmark score: 8167 versus 6764. That is a difference of roughly 1400 points, or about 21%. The percentile ranking reinforces the separation: the GTX 980 sits at the 43rd percentile of all GPUs, while the R7 M370 sits at the 38th percentile.

Context from the nearest rivals adds perspective. The GTX 980's closest rival, the NVIDIA GeForce GTX 950M, averages 8135, just 0.4% behind. The AMD Radeon R9 M360 is 0.5% behind, the NVIDIA GeForce 945M is 0.8% behind, and the NVIDIA GRID K2 is 1.1% behind. So the GTX 980's score is tightly clustered with mobile and professional parts that are much closer in performance than the R7 M370.

The R7 M370's nearest rivals show a different competitive landscape. The AMD FirePro M5100 leads it by 1%, while the NVIDIA GeForce GT 1010 trails by 1%, the AMD Radeon R7 M460 trails by 2.3%, and the NVIDIA GeForce GTX 675M leads by 2.6%. These deltas are small, indicating the R7 M370 sits in a tightly packed mid-range mobile segment. The GTX 980, by contrast, sits near the top of its own peer group, and both cards are far above the R7 M370 in every direct comparison.

The GTX 980 has 2 wins in the head-to-head data; the R7 M370 has none.

Specification Differences

The two GPUs differ in nearly every measurable specification field recorded in the database.

• Chip and architecture: GM204 with Maxwell 2.0 versus Litho with GCN 1.0
• Process node: both 28 nm, but the GTX 980 uses 5,200 million transistors on 398 mm²; the R7 M370 uses 950 million on 77 mm²
• Transistor density: 13.1M per mm² versus 12.3M per mm²
• Base clock: 1127 MHz versus 875 MHz
• Boost clock: 1216 MHz versus 960 MHz
• Memory clock: 1753 MHz (7 Gbps effective) versus 900 MHz (3.6 Gbps effective)
• Memory size: 4 GB versus 2 GB
• Memory bus width: 256 bit versus 128 bit
• Memory bandwidth: 224.4 GB/s versus 57.60 GB/s
• Shading units: 2048 versus 384
• Texture mapping units: 128 versus 24
• ROPs: 64 versus 8
• Pixel rate: 77.82 GPixel/s versus 7.680 GPixel/s
• Texture rate: 155.6 GTexel/s versus 23.04 GTexel/s
• FP32 compute: 4.981 TFLOPS versus 737.3 GFLOPS
• TDP: 165 W for the GTX 980; no recorded value for the R7 M370
• Slot width: dual-slot for the GTX 980; none recorded for the R7 M370
• Power connectors: 2x 6-pin for the GTX 980; none recorded for the R7 M370
• Suggested PSU: 450 W for the GTX 980; none recorded for the R7 M370
• Bus interface: PCIe 3.0 x16 versus PCIe 3.0 x8
• Display outputs: 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2 for the GTX 980; none recorded for the R7 M370
• DirectX: 12 (12_1) versus 12 (11_1)
• OpenGL: both 4.6
• Vulkan: 1.4 versus 1.2.170
• Dimensions: the GTX 980 measures 267 mm x 111 mm x 40 mm; no dimensions recorded for the R7 M370
• Release date: 2014-09-18 versus 2015-05-04
• Launch MSRP: 549 USD for the GTX 980; none recorded for the R7 M370
• Production status: both end-of-life

Every specification that can be compared shows the GTX 980 ahead. The R7 M370's only comparative advantages are its smaller die, lower transistor count, and later release date, which are not performance advantages.

Where Each One Wins

The GTX 980 wins everywhere the database records a direct comparison. In Geekbench OpenCL, it leads by 391%. In Geekbench Vulkan, it leads by 248.7%. The average benchmark score favors the GTX 980 by roughly 21%, and its percentile ranking is higher at 43 versus 38. For any workload that stresses compute throughput, texture fill, pixel fill, or memory bandwidth, the GTX 980 is the clear choice.

The use case for the GTX 980 is high-end desktop gaming and compute at 1080p or higher. Its 4 GB frame buffer, 256-bit bus, and 224.4 GB/s bandwidth support high-resolution textures and demanding effects. Its 2048 shading units and 4.981 TFLOPS of FP32 throughput make it suitable for OpenCL and Vulkan compute tasks where the R7 M370 cannot compete. The dual-slot cooler, dual 6-pin power connectors, and 450 W suggested PSU indicate a card designed for full-size desktop builds with adequate power delivery.

The R7 M370 has no benchmark wins in the head-to-head data. Its role is limited to lighter mobile or small-form-factor workloads. With only 384 shading units, 8 ROPs, and 57.60 GB/s of bandwidth, it is suited for modest 3D workloads, basic video playback, and light productivity tasks. Its PCIe 3.0 x8 interface and lack of recorded power or cooling requirements suggest an implementation designed for power-constrained systems. The R7 M370's nearest rivals, including the AMD FirePro M5100, NVIDIA GeForce GT 1010, and AMD Radeon R7 M460, all sit within a few percentage points, confirming it occupies a narrow performance band in the low-to-mid range.

The database shows two GPUs that are not competitors in any practical sense. The GTX 980 is a high-end desktop part from 2014 with a launch MSRP of 549 USD; the R7 M370 is a low-end mobile part from 2015. The GTX 980's nearest rivals are the GTX 950M, R9 M360, GeForce 945M, and GRID K2, all scoring between 8080 and 8135. The R7 M370's nearest rivals are the FirePro M5100, GT 1010, R7 M460, and GTX 675M, all scoring between 6612 and 6946. The two peer groups do not overlap.

For buyers or system integrators choosing between these two, the GTX 980 is the only option when performance matters. The R7 M370 only makes sense in contexts where the GTX 980 cannot physically be installed, such as thin laptops or low-power embedded systems. The recorded data offers no scenario where the R7 M370 outperforms the GTX 980, and the architecture gap, memory subsystem gap, and compute gap all point the same direction.