

NVIDIA B200 wins 9 of 9 benchmarks, averaging 320.1% faster.
NVIDIA Quadro RTX 6000 (Turing)'s numbers are anchored estimates calibrated against our measured cards, pending first-party measurement. Treat small gaps as ties.
The gap is widest in Stable Diffusion XL, where NVIDIA B200 leads by 676% (46.12 vs 5.94 images/min); the closest fight is Qwen3 4B (154% apart); VRAM decides part of this one: NVIDIA B200 runs 145 of our 12 AI workloads while the other card runs 4, models that don't fit score zero.
| Benchmark | NVIDIA B200 | NVIDIA Quadro RTX 6000 (Turing) | Difference |
|---|---|---|---|
| Qwen3 4B tok/s | 317.93 | 125.23 | +154% |
| Llama 3.1 8B tok/s | 274.41 | 84.21 | +226% |
| Qwen2.5-Coder 14B tok/s | 150.96 | 46.54 | +224% |
| Qwen3 32B tok/s | 78.56 | 0 | n/a |
| Llama 3.3 70B tok/s | 44.54 | 0 | n/a |
| Stable Diffusion XL images/min | 46.12 | 5.94 | +676% |
| FLUX.1 dev images/min | 13.136 | 0 | n/a |
| FLUX.1 Kontext dev images/min | 5.721 | 0 | n/a |
| Qwen-Image-Edit images/min | 4.86 | 0 | n/a |
How long each card takes to finish a complete pipeline, not just one model. NVIDIA B200 is faster on 1 of 1; NVIDIA Quadro RTX 6000 (Turing) on 0.
| Workflow | NVIDIA B200 | NVIDIA Quadro RTX 6000 (Turing) | Difference |
|---|---|---|---|
| Full codebase review | 6.6 min | 21.5 min | NVIDIA B200 3.24x faster |
| NVIDIA B200 | NVIDIA Quadro RTX 6000 (Turing) | |
|---|---|---|
| VRAM | 192GB | 24GB |
| Architecture | Blackwell | Turing (TU102) |
| Memory bandwidth | 8 TB/s | 672 GB/s |
| Boost clock | n/a | 1,770 MHz |
| TDP | 1000 W | 260 W |
| Launch MSRP | $40,000 | $6,300 |
| Release | 2025-02-01 | 2018-08-14 |
NVIDIA B200 full review · NVIDIA Quadro RTX 6000 (Turing) full review · All AI & Machine Learning rankings