AMD Radeon 890M vs NVIDIA GeForce GTX 980 Comparison

AMD
RADEON

AMD Radeon 890M

CORE STATE Strix Point
VRAM System Shared
CLOCK SPEED 2900 MHz
TDP 15 W
BUS WIDTH System Shared
ARCHITECTURE RDNA 3.5
nm
PROCESS 4 nm
LAUNCH DATE 2024
VS
NVIDIA
GEFORCE

GeForce GTX 980

CORE STATE GM204
VRAM 4 GB
CLOCK SPEED 1216 MHz
TDP 165 W
BUS WIDTH 256 bit
ARCHITECTURE Maxwell 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2014

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
590
474
geekbench_opencl
37,254
34,676
geekbench_vulkan
40,808
22,543
passmark_directx_10
33
53
passmark_directx_11
73
83
passmark_directx_12
37
46
passmark_directx_9
97
164
passmark_g2d
979
792
passmark_g3d
8,076
11,095
passmark_gpu_compute
4,157
4,753
geekbench_metal
N/A
15,163

Analysis: AMD Radeon 890M vs NVIDIA GeForce GTX 980

FAQ

Q: How does the AMD Radeon 890M compare to the NVIDIA GeForce GTX 980 in overall average benchmark score?

A: The AMD Radeon 890M records an average benchmark score of 9210, while the NVIDIA GeForce GTX 980 records 8167. The 890M sits at the 45th percentile of all GPUs, and the GTX 980 sits at the 43rd percentile.

Q: Which GPU wins the most head-to-head benchmarks?

A: The NVIDIA GeForce GTX 980 wins 6 of the 10 head-to-head benchmark comparisons, while the AMD Radeon 890M wins 4. The GTX 980's wins are concentrated in DirectX 10, 11, 12, 9, G3D, and GPU compute tests.

Q: In which benchmark does the AMD Radeon 890M show its largest lead over the GTX 980?

A: The largest lead for the 890M is in the Geekbench Vulkan test, where it scores 40808 versus the GTX 980's 22543, a delta of 81%. The 890M also leads by 24.5% in 3DMark Steel Nomad DX12.

Q: In which benchmark does the NVIDIA GeForce GTX 980 show its largest lead?

A: The GTX 980's largest lead is in Passmark DirectX 9, where it scores 164 versus the 890M's 97, a delta of 40.9%. It also leads by 37.7% in Passmark DirectX 10.

Q: What are the nearest rivals to each GPU according to the database?

A: The AMD Radeon 890M's nearest rivals are the AMD Radeon Vega 8 (avg score 9221, delta -0.1%), NVIDIA GeForce GTX 960 (avg 9273, delta -0.7%), NVIDIA GeForce GTX 465 (avg 9294, delta -0.9%), and NVIDIA GeForce GTX 850M (avg 9302, delta -1%). The GTX 980's nearest rivals are the NVIDIA GeForce GTX 950M (avg 8135, delta 0.4%), AMD Radeon R9 M360 (avg 8129, delta 0.5%), NVIDIA GeForce 945M (avg 8099, delta 0.8%), and NVIDIA GRID K2 (avg 8080, delta 1.1%).

Q: What is the production status and launch MSRP of each GPU?

A: The AMD Radeon 890M is listed as Active in production and has no launch MSRP recorded. The NVIDIA GeForce GTX 980 is End-of-life and had a launch MSRP of 549 USD.

Architecture Differences

The AMD Radeon 890M and NVIDIA GeForce GTX 980 represent two fundamentally different design philosophies separated by a decade of GPU evolution. The 890M is built on the RDNA 3.5 architecture using the Strix Point chip, fabricated on a 4 nm process at TSMC. It belongs to the Navi III IGP generation for Strix Point Mobile. The GTX 980 uses the Maxwell 2.0 architecture with the GM204 chip, built on a 28 nm process, also at TSMC, and belongs to the GeForce 900 generation.

The transistor counts highlight the process node advantage. The 890M packs 34,000 million transistors into a 233 mm² die, yielding a transistor density of 145.9 million per square millimeter. The GTX 980 contains 5,200 million transistors on a 398 mm² die, with a density of just 13.1M per square millimeter. The 890M's density is roughly 11 times higher per unit area, a direct consequence of the 4 nm versus 28 nm process gap.

The 890M is an integrated graphics processor (IGP) with a TDP of 15 W and no power connectors, while the GTX 980 is a dual-slot discrete card with a 165 W TDP and requires two 6-pin power connectors. The 890M uses system shared memory, with bandwidth described as system dependent. The GTX 980 has 4 GB of dedicated GDDR5 memory on a 256 bit bus, delivering 224.4 GB/s of bandwidth.

The 890M features 1024 shading units, 64 texture mapping units, 32 raster operations pipelines, and 16 ray tracing cores. The GTX 980 has 2048 shading units, 128 TMUs, and 64 ROPs, but no ray tracing cores. The 890M supports DirectX 12 Ultimate (12_2), while the GTX 980 supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The 890M is an integrated part with no dedicated slot width, while the GTX 980 is dual-slot at 267 mm long, 111 mm tall, and 40 mm wide. The 890M uses PCIe 4.0 x8, and the GTX 980 uses PCIe 3.0 x16.

Head-to-Head Benchmarks

The recorded data shows a clear split between modern and legacy workloads. The AMD Radeon 890M wins in 3DMark Steel Nomad DX12 with a score of 590 against 474, a 24.5% lead. In Geekbench Vulkan, the 890M's 40,808 score crushes the GTX 980's 22,543, a 81% difference. The Geekbench OpenCL result also favors the 890M: 37,254 versus 34,676, a 7.4% advantage. In Passmark G2D, the 890M scores 979 versus 792, a 23.6% lead.

The NVIDIA GeForce GTX 980 dominates the older DirectX legacy tests. It wins Passmark DirectX 9 by 40.9% (164 versus 97) and DirectX 10 by 37.7% (53 versus 33). The GTX 980 also leads in Passmark DirectX 11 (83 versus 73, a 12% margin) and DirectX 12 (46 versus 37, a 19.6% margin). The GTX 980 wins Passmark G3D with 11,095 versus 8,076, a 27.2% lead, and Passmark GPU Compute with 4,753 versus 4,157, a 12.5% lead.

These results indicate a GPU that is strong in modern APIs and compute, but weaker in legacy rasterization performance. The 890M's 5.939 TFLOPS FP32 output is actually higher than the GTX 980's 4.981 TFLOPS, and the 890M also has a higher pixel rate (92.80 GPixel/s versus 77.82 GPixel/s) and texture rate (185.6 GTexel/s versus 155.6 GTexel/s). However, the GTX 980's hardware and drivers deliver more consistent results in older DirectX 9/10/11 pipelines.

The wins split 4 to 6 in favor of the GTX 980, but the magnitude matters. The 890M's Vulkan win is enormous, at 81%, while the GTX 980's largest win is 40.9% in DirectX 9. The 890M loses the G3D test by a substantial 27.2%, which is the overall gaming proxy used in the database.

Specification Differences

The following fields differ between the two GPUs:

  • Process Node: 4 nm (890M) versus 28 nm (GTX 980)
  • Transistors: 34,000 million versus 5,200 million
  • Die Size: 233 mm² versus 398 mm²
  • Transistor Density: 145.9M / mm² versus 13.1M / mm²
  • Base Clock: 400 MHz versus 1127 MHz
  • Boost Clock: 2900 MHz versus 1216 MHz
  • Memory Type: System Shared versus GDDR5
  • Memory Size: System Shared versus 4 GB
  • Memory Bus Width: System Shared versus 256 bit
  • Memory Bandwidth: System Dependent versus 224.4 GB/s
  • Shading Units: 1024 versus 2048
  • TMUs: 64 versus 128
  • ROPs: 32 versus 64
  • RT Cores: 16 versus null
  • Pixel Rate: 92.80 GPixel/s versus 77.82 GPixel/s
  • Texture Rate: 185.6 GTexel/s versus 155.6 GTexel/s
  • FP32: 5.939 TFLOPS versus 4.981 TFLOPS
  • TDP: 15 W versus 165 W
  • Slot Width: IGP versus Dual-slot
  • Power Connectors: None versus 2x 6-pin
  • Bus Interface: PCIe 4.0 x8 versus PCIe 3.0 x16
  • Display Outputs: Portable Device Dependent versus 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2
  • DirectX Support: 12 Ultimate (12_2) versus 12 (12_1)
  • Dimensions: null versus 267 mm (length), 111 mm (height), 40 mm (width)
  • Production Status: Active versus End-of-life
  • Release Date: 2024-07-14 versus 2014-09-18
  • Predecessor: Navi II IGP versus GeForce 700
  • Successor: null versus GeForce 10
  • Launch MSRP: null versus 549 USD

The 890M has a much lower TDP and physically smaller footprint, while the GTX 980 offers twice as many shading units and texture units. The 890M compensates with a much higher boost clock (2900 MHz versus 1216 MHz) and superior fill rates. The GTX 980 has a fixed 4 GB frame buffer, while the 890M relies on system memory.

Where Each One Wins

The AMD Radeon 890M wins in modern API scenarios and compute-heavy workloads. Its 81% lead in Geekbench Vulkan is the single largest advantage in the entire comparison, indicating strong driver support for Vulkan. The 24.5% lead in 3DMark Steel Nomad DX12 confirms its capability in current DirectX 12 titles. The 890M also wins Geekbench OpenCL and Passmark G2D, with 7.4% and 23.6% leads respectively. These wins suggest the 890M is suited for applications that leverage Vulkan, DX12, and OpenCL compute, such as modern game engines and general-purpose GPU compute tasks. Its 16 ray tracing cores further support modern rendering features, although no ray tracing benchmark scores are present in the database.

The NVIDIA GeForce GTX 980 wins in legacy DirectX workloads and overall GPU throughput as measured by Passmark G3D. Its 40.9% lead in DirectX 9 and 37.7% lead in DirectX 10 show strong compatibility with older game engines and applications that still rely on those pipelines. It also holds leads in DirectX 11 (12%) and DirectX 12 (19.6%), plus a 12.5% lead in GPU compute. The G3D score of 11095 versus 8076 is a 27.2% advantage, which is a significant overall gaming performance metric.

For practical use, the 890M is a low-power integrated GPU that fits in thin mobile devices, and its wins in modern APIs make it a strong choice for DX12 and Vulkan games. The GTX 980, despite its age, remains a capable discrete card for older titles and general 3D rendering, but its End-of-life status and 165 W power draw are disadvantages. The 890M's 24.5% lead in 3DMark Steel Nomad DX12 and 81% lead in Vulkan position it as the better choice for anyone running current API games, while the GTX 980's 27.2% lead in G3D and 40.9% lead in DX9 show its strength in legacy software. The database shows 4 wins for the 890M and 6 for the GTX 980, but the wins that matter for future-proofing belong clearly to the 890M.

DETAILED SPECIFICATIONS

SPECIFICATION
890M
GTX 980
Core Specs
Shading Units
1,024
2,048 +100.0%
Shaders
1,024
2,048 +100.0%
TMUs
64
128 +100.0%
ROPs
32
64 +100.0%
Compute Units
16
Clocks
Base Clock
400 MHz
1127 MHz
Boost Clock
2900 MHz
1216 MHz
Memory Clock
System Shared
1753 MHz 7 Gbps effective
Memory
Memory Size
System Shared
4 GB
VRAM (MB)
4,096
Memory Type
System Shared
GDDR5
Memory Bus
System Shared
256 bit
Bandwidth
System Dependent
224.4 GB/s
Cache
L1 Cache
128 KB per Array
48 KB (per SMM)
L2 Cache
2 MB
2 MB
L0 Cache
32 KB per WGP
Performance
Pixel Rate
92.80 GPixel/s
77.82 GPixel/s
Texture Rate
185.6 GTexel/s
155.6 GTexel/s
FP32 (TFLOPS)
5.939 TFLOPS
4.981 TFLOPS
FP64 (TFLOPS)
371.2 GFLOPS (1:16)
155.6 GFLOPS (1:32)
FP16 (TFLOPS)
5.939 TFLOPS (1:1)
AI/RT
RT Cores
16
Power
TDP
15 W
165 W
TDP (W)
15
165 +1000.0%
Suggested PSU
450 W
Power Connectors
None
2x 6-pin
Architecture
Architecture
RDNA 3.5
Maxwell 2.0
GPU Name
Strix Point
GM204
Generation
Navi III IGP (Strix Point Mobile)
GeForce 900
Process Size
4 nm
28 nm
Transistors
34,000 million
5,200 million
Die Size
233 mm²
398 mm²
Foundry
TSMC
TSMC
Density
145.9M / mm²
13.1M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
5.2
Shader Model
6.8
6.8
Physical
Slot Width
IGP
Dual-slot
Length
267 mm 10.5 inches
Height
111 mm 4.4 inches
Outputs
Portable Device Dependent
1x DVI1x HDMI 2.03x DisplayPort 1.2
Bus Interface
PCIe 4.0 x8
PCIe 3.0 x16
Other
Launch Price
549 USD
Production
Active
End-of-life
Predecessor
Navi II IGP
GeForce 700
Successor
GeForce 10
View Radeon 890M Details View GeForce GTX 980 Details