AMD Radeon 760M vs AMD Radeon HD 8690M Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark between these two GPUs is Geekbench OpenCL, and the result is decisive. The AMD Radeon 760M scores 20,255, while the AMD Radeon HD 8690M scores 6,137. That is a delta of -69.7% from the 760M's perspective, meaning the 760M delivers roughly 3.3 times the raw compute performance in this test. The HD 8690M wins zero head-to-head comparisons; the 760M wins one.

Looking at the broader benchmark landscape, the HD 8690M's average benchmark score sits at 6,137, placing it in the 36th percentile of all GPUs. Its nearest rivals are clustered tightly around it: the Intel Iris Pro Graphics 6200 trails by just 0.3%, the NVIDIA RTX A400 is 1% behind, and the GeForce MX230 is also 1% behind. The AMD Radeon HD 6950 leads the HD 8690M by 1.2%. These are all essentially neck-and-neck results — the HD 8690M is in a crowded performance tier where a few percentage points separate competitors.

The Radeon 760M, despite its much higher OpenCL score, actually sits at a lower 35th percentile overall. Its average benchmark score is 6,019, which is slightly below the HD 8690M's average. This seems contradictory until you examine the full benchmark suite. The 760M's scores vary wildly: it hits 30,336 in Geekbench Vulkan, 5,310 in Passmark G3D, and 2,840 in Passmark GPU Compute, but it also posts very low numbers in Passmark DirectX tests — 19 in DX10, 52 in DX11, 25 in DX12, and 65 in DX9. The 2D score of 890 is respectable, but those DirectX scores drag the average down. The 760M's nearest rivals reflect this mixed profile: AMD Radeon RX 6400 is 0.3% ahead, NVIDIA GeForce GTX 770M is 0.3% ahead, and NVIDIA RTX PRO 6000 Blackwell Server is 0.4% ahead, while the Quadro P2000 trails by 0.5%. So the 760M is competing with a wide range of discrete and integrated parts depending on the workload.

Where Each One Wins

The HD 8690M's advantage is consistency. It has only one benchmark score — that 6,137 OpenCL result — and it sits comfortably at the 36th percentile. For a GPU from 2013, this represents a stable, predictable performance level. In the OpenCL test, it beats the Iris Pro 6200 by 0.3% and the RTX A400 by 1%, meaning it holds its own against much newer integrated and entry-level discrete parts. The HD 8690M is a straightforward, no-surprises performer for compute workloads that use OpenCL.

The Radeon 760M wins decisively in raw compute. Its OpenCL score of 20,255 is more than triple the HD 8690M's. In Vulkan, it reaches 30,336, which is a strong result for an integrated GPU. The 760M also shows competence in general 3D rendering with a Passmark G3D score of 5,310 and a G2D score of 890. Where the 760M struggles is in legacy DirectX workloads — the Passmark DX9 through DX12 scores of 65, 19, 52, and 25 respectively indicate that older API paths are not its strength. This is a GPU built for modern APIs and compute, not for backward compatibility.

For gaming, the data suggests the 760M will handle newer DirectX 12 Ultimate titles far better than the HD 8690M, which is limited to DirectX 12 (11_1). But for older games or applications that rely on DirectX 9-11, the HD 8690M's simpler architecture might actually provide more consistent frame pacing, given the 760M's very low scores in those specific tests. The 760M's 3DMark Steel Nomad DX12 score of 400 gives some indication of modern gaming performance, though there is no comparable DX12 score for the HD 8690M to compare against.

Architecture Differences

The architectural gap between these two GPUs spans a decade of AMD design philosophy. The HD 8690M uses the Sun chip based on GCN 1.0 architecture, manufactured on a 28 nm process at TSMC. It packs 690 million transistors into a 56 mm² die, yielding a transistor density of 12.3 million per mm². This is an old-school discrete GPU design with dedicated GDDR5 memory — 2 GB on a 64-bit bus delivering 32.00 GB/s of bandwidth. Its memory clocks at 1000 MHz with 4 Gbps effective transfer rate.

The Radeon 760M uses the Phoenix chip based on RDNA 3.0 architecture, built on a 4 nm process, also at TSMC. This is a massive integrated GPU that shares the die with a CPU. The Phoenix chip contains 25,390 million transistors on a 178 mm² die, giving a transistor density of 142.6 million per mm². That is over 11 times the transistor density of the Sun chip. The 760M uses system shared memory — no dedicated VRAM — with bandwidth that is system dependent. Its base clock is lower at 800 MHz, but the boost clock reaches 2,599 MHz, compared to the HD 8690M's 925 MHz base and 975 MHz boost.

Compute resources differ substantially. The 760M has 512 shading units, 32 texture mapping units, and 16 ROPs, plus 8 ray tracing cores. The HD 8690M has 320 shading units, 20 TMUs, and 8 ROPs, with no ray tracing support. The pixel rate tells the story: the 760M delivers 41.58 GPixel/s versus 7.800 GPixel/s for the HD 8690M. Texture rate is 83.17 GTexel/s versus 19.50 GTexel/s. FP32 compute is 5.323 TFLOPS versus 624.0 GFLOPS — a 8.5x difference. The 760M also has FP16 capability at 5.323 TFLOPS (1:1), while the HD 8690M has no FP16 support listed.

API support highlights the generational leap. The 760M supports DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6. The HD 8690M only reaches DirectX 12 (11_1), Vulkan 1.2.170, and OpenGL 4.6. The 760M also has 8 ray tracing cores, enabling hardware-accelerated ray tracing that the HD 8690M cannot do at all. The bus interface moves from PCIe 3.0 x8 to PCIe 4.0 x8, doubling potential bandwidth to the host system.

The 760M is an integrated GPU (IGP) with a 15 W TDP and no power connectors — it draws power from the motherboard. The HD 8690M has no TDP listed in the data, but as a discrete mobile GPU, it would have had its own power delivery. The 760M's display outputs are motherboard dependent, while the HD 8690M's display outputs are not specified.

The Verdict

If you are choosing between these two strictly on the benchmark data, the Radeon 760M is the clear winner for modern workloads. Its OpenCL score is 230% higher than the HD 8690M's, and its Vulkan score of 30,336 demonstrates strong compute capability. The 760M supports ray tracing, DirectX 12 Ultimate, and Vulkan 1.4 — features that the HD 8690M simply cannot offer. For gaming, content creation, or any compute-heavy task built for modern APIs, the 760M is the only sensible choice.

However, the HD 8690M is not without its niche. Its single OpenCL score is remarkably consistent with its nearest rivals — it beats the Iris Pro 6200 and RTX A400 by small margins. If you are running legacy applications that rely on older DirectX paths, the HD 8690M may actually be more reliable. The 760M's Passmark DX9-DX12 scores (65, 19, 52, 25) suggest severe performance degradation in those legacy paths, while the HD 8690M's GCN 1.0 architecture was designed for an era when DirectX 11 was the standard. The 760M's 35th percentile overall ranking versus the HD 8690M's 36th percentile is misleading — the averages hide the fact that the 760M is a modern part with specific strengths and weaknesses, not a uniformly slow GPU.

The production status tells the practical story: the HD 8690M is end-of-life, released in late February 2013, while the 760M is active, released in late January 2024. The HD 8690M's predecessor is London and its successor is Gem System. The 760M's predecessor is Navi II IGP with no successor listed. If you are building a new system today, the 760M is the only one you can buy new. If you are maintaining an old laptop with a soldered HD 8690M, it will still handle basic OpenCL compute and older games, but it will struggle with anything modern.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The AMD Radeon 760M scores 20,255 in Geekbench OpenCL, while the AMD Radeon HD 8690M scores 6,137. The 760M leads by 69.7%.

Q: How does the HD 8690M compare to its nearest rivals?

A: The HD 8690M's average score of 6,137 is 0.3% ahead of the Intel Iris Pro Graphics 6200, 1% ahead of both the NVIDIA RTX A400 and GeForce MX230, and 1.2% behind the AMD Radeon HD 6950.

Q: Does the Radeon 760M support ray tracing?

A: Yes, the Radeon 760M has 8 ray tracing cores and supports DirectX 12 Ultimate (12_2), which includes ray tracing features. The HD 8690M has no ray tracing cores and only supports DirectX 12 (11_1).

Q: What memory configurations do these GPUs use?

A: The HD 8690M uses 2 GB of dedicated GDDR5 memory on a 64-bit bus with 32.00 GB/s bandwidth. The 760M uses system shared memory with system-dependent bandwidth.

Q: Which GPU has the higher boost clock?

A: The Radeon 760M boosts to 2,599 MHz, while the HD 8690M boosts to 975 MHz. The 760M also has a lower base clock at 800 MHz versus 925 MHz for the HD 8690M.

Q: What are the production status of these two GPUs?

A: The HD 8690M is end-of-life, released on February 28, 2013. The Radeon 760M is active, released on January 30, 2024.

Specification Differences

| Specification | AMD Radeon HD 8690M | AMD Radeon 760M |

|---|---|---|

| Architecture | GCN 1.0 | RDNA 3.0 |

| Process Node | 28 nm | 4 nm |

| Transistors | 690 million | 25,390 million |

| Die Size | 56 mm² | 178 mm² |

| Transistor Density | 12.3M / mm² | 142.6M / mm² |

| Base Clock | 925 MHz | 800 MHz |

| Boost Clock | 975 MHz | 2599 MHz |

| Memory Type | GDDR5 | System Shared |

| Memory Size | 2 GB | System Shared |

| Memory Bus Width | 64 bit | System Shared |

| Memory Bandwidth | 32.00 GB/s | System Dependent |

| Shading Units | 320 | 512 |

| TMUs | 20 | 32 |

| ROPs | 8 | 16 |

| Ray Tracing Cores | None | 8 |

| Pixel Rate | 7.800 GPixel/s | 41.58 GPixel/s |

| Texture Rate | 19.50 GTexel/s | 83.17 GTexel/s |

| FP32 Performance | 624.0 GFLOPS | 5.323 TFLOPS |

| FP16 Performance | None | 5.323 TFLOPS (1:1) |

| TDP | Not specified | 15 W |

| Bus Interface | PCIe 3.0 x8 | PCIe 4.0 x8 |

| DirectX Support | 12 (11_1) | 12 Ultimate (12_2) |

| Vulkan Support | 1.2.170 | 1.4 |

| Production Status | End-of-life | Active |

| Release Date | 2013-02-28 | 2024-01-30 |

| Predecessor | London | Navi II IGP |

| Successor | Gem System | None |