Intel Arc B580

The B580's strongest measured trait is frames per $100 at 27.5 fps/$100, which puts it in the 97th percentile — that metric describes raw frames bought per hundred dollars, before any age weighting. Its weakest is bandwidth per pixel at 1,806 B/px (48th percentile). That is a wide spread for a single card: it is specialised rather than balanced, and whether it suits you depends on which of the two you actually load.

The B580 turns a 190W board power budget into 68.5 fps at 1440p, or 0.36 fps/W against a pool median of 0.32 fps/W. Power, not transistor count, is the binding constraint on a modern GPU — Dennard scaling stopped holding around 2005, and Esmaeilzadeh and colleagues showed at ISCA 2011 that the fraction of a chip that can be powered at full speed shrinks with every node (“dark silicon”). Frames per watt is the shortest honest summary of what an architecture is doing with that budget.

For scale: the closest Intel card from an earlier generation is the Intel Arc A770 (2022), at 59.8 fps and 225W. The B580 is 15% faster while drawing 35W less.

Every rendered pixel has to be fed from memory. At 1440p the B580 has 1,806 B/px of memory bandwidth available per pixel it draws, against a median of 1,808 B/px — roughly in balance for its performance class. This is the roofline model applied to a game frame: Williams, Waterman and Patterson (Communications of the ACM, 2009) showed that any workload runs into either a compute ceiling or a memory-bandwidth ceiling, and that the ratio of the two is what decides which one you hit.

The B580 ranks #36 in 3DMark Steel Nomad but #41 on the 1440p game average — 5 places lower in real games than the synthetic implies. Steel Nomad is a 4K, non-ray-traced pass with heavy async compute and no upscaling, so it rewards raw shader and bandwidth throughput and ignores driver overhead, geometry front-end limits, and everything a game engine does outside the compute path. A gap this size means the hardware on paper is ahead of what the driver and engine mix currently extract from it.

On memory capacity, the B580 carries 12GB against a median of 8GB across the 5 other cards within 10% of its 1440p frame rate. It carries more memory than its performance class typically ships with, which mostly matters for high-resolution textures, local AI models, and viewport-heavy creative work rather than frame rate.

Method: percentiles are computed over the 77 non-legacy cards with a 1440p figure. Frame rates come from Tom's Hardware GPU hierarchy; specifications from manufacturer datasheets. Theoretical FP32 TFLOPS is deliberately not used as a cross-vendor comparison — RDNA 3 and 4 dual-issue FP32 doubles the paper figure without doubling game performance, and AMD itself declined to count it as extra shaders. The measured Steel Nomad score is used as the compute proxy instead. GPURanker does not run its own benchmarks.