AI GPU Benchmark Results
Every benchmark number in our database, with its source and tier. Filter by workload or source tier; sort by any column. Tier 1 = manufacturer/benchmark-DB, Tier 2 = independent reviews, Tier 3 = community or estimated.
97sourced results
26products covered
64GPUs in database
Honest coverage: our current benchmark set covers LLM inference (tokens/s) and Stable Diffusion image generation on flagship and mid-range cards. Gaming FPS and video-generation numbers are not yet sourced — they will appear here when we have verifiable sources. See the methodology and tier definitions.
Filter results
97 benchmark results
| GPU | Workload | Model / config | Result | Source tier | Source |
|---|---|---|---|---|---|
| Arc B580 | Image generation | SDXL Turbo · FP16 · ComfyUI | 18 img/min EST | T2 | TechPowerUp GPU Reviews |
| GeForce RTX 3090 | Image generation | SDXL Turbo · FP16 · ComfyUI | 45 img/min | T2 | Puget Systems Hardware Testing |
| GeForce RTX 4060 Ti 16GB | Image generation | SDXL Turbo · FP16 · ComfyUI | 28 img/min | T2 | TechPowerUp GPU Reviews |
| GeForce RTX 4080 SUPER | Image generation | SDXL Turbo · FP16 · ComfyUI | 58 img/min | T2 | TechPowerUp GPU Reviews |
| GeForce RTX 4090 | Image generation | SDXL Turbo · FP16 · ComfyUI | 80 img/min | T2 | Tom's Hardware GPU Benchmarks 2025 |
| GeForce RTX 4090 | Image generation | Stable Diffusion 1.5 · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 1.188 s/image) | 5,260 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 4090 | Image generation | Stable Diffusion 1.5 INT8 · INT8 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.503 s/image) | 62,160 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 4090 | Image generation | Stable Diffusion XL · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 7.461 s/image) | 5,025 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 5080 | Image generation | SDXL Turbo · FP16 · ComfyUI | 65 img/min | T2 | TechPowerUp GPU Reviews |
| GeForce RTX 5080 | Image generation | Stable Diffusion 1.5 · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 1.344 s/image) | 4,650 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 5080 | Image generation | Stable Diffusion 1.5 INT8 · INT8 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.561 s/image) | 55,683 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 5080 | Image generation | Stable Diffusion XL · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 8.808 s/image) | 4,257 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 5090 | Image generation | SDXL Turbo · FP16 · ComfyUI | 120 img/min | T2 | Tom's Hardware GPU Benchmarks 2025 |
| GeForce RTX 5090 | Image generation | Stable Diffusion 1.5 · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.763 s/image) | 8,193 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 5090 | Image generation | Stable Diffusion 1.5 INT8 · INT8 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.394 s/image) | 79,272 score | T2 | StorageReview GPU Reviews |
| GeForce RTX 5090 | Image generation | Stable Diffusion XL · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 5.223 s/image) | 7,179 score | T2 | StorageReview GPU Reviews |
| Radeon RX 7900 XTX | Image generation | SDXL Turbo · FP16 · ComfyUI (ROCm) | 40 img/min | T2 | Tom's Hardware GPU Benchmarks 2025 |
| RTX 6000 Ada | Image generation | SDXL Turbo · FP16 · ComfyUI | 75 img/min | T2 | Puget Systems Hardware Testing |
| RTX 6000 Ada | Image generation | Stable Diffusion 1.5 · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 1.477 s/image) | 4,230 score | T2 | StorageReview GPU Reviews |
| RTX 6000 Ada | Image generation | Stable Diffusion 1.5 INT8 · INT8 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 0.559 s/image) | 55,901 score | T2 | StorageReview GPU Reviews |
| RTX 6000 Ada | Image generation | Stable Diffusion XL · FP16 · UL Procyon AI Image Generation (Standardized UL Procyon suite; same lab platform (ThreadRipper 7980X, driver 571.86); 12.323 s/image) | 3,043 score | T2 | StorageReview GPU Reviews |
| RTX A6000 | Image generation | SDXL Turbo · FP16 · ComfyUI | 35 img/min | T2 | Puget Systems Hardware Testing |
How these numbers are sourced
Every row links to its original source. Tier 1 comes from manufacturers or standardized benchmark databases (MLPerf), Tier 2 from independent reviews (Tom's Hardware, TechPowerUp, Puget Systems), Tier 3 from community measurements or our own scaling estimates — always labeled EST when estimated. Read the full benchmark methodology.
Compare any two GPUs head-to-head in the comparison tool, or browse value rankings.