A paid production workload on the reference fleet, measured on GeForce RTX 4080 and GeForce RTX 5090 on the same days. One workload, its own cells — never averaged with any other workload, because cross-workload aggregation is the substitution error this project exists to expose.
| DAY | GOODPUT GeForce RTX 4080 / GeForce RTX 5090 | ATTEMPTS | COMPLETIONS | CARDS |
|---|---|---|---|---|
| 2026-08-21 | 0.44× | 80 / 290 | 76 / 284 | 2 / 6 |
| 2026-08-22 | 0.34× | 113 / 424 | 105 / 417 | 2 / 6 |
| 2026-08-23 | 0.33× | 108 / 295 | 104 / 292 | 2 / 6 |
| 2026-08-24 | 0.30× | 95 / 252 | 94 / 248 | 2 / 4 |
| 2026-08-26 | 0.37× | 118 / 308 | 111 / 298 | 2 / 6 |
| 2026-08-27 | 0.29× | 92 / 305 | 85 / 299 | 2 / 6 |
| 2026-08-29 | 0.27× | 100 / 50 | 96 / 48 | 2 / 4 |
The measured pair page for these deployments: side-by-side cells. Downloads: ratio cells, value board, the rental prices these were costed at.