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 | 0.34× | 65 / 104 | 50 / 102 | 2 / 6 |
| 2026-08-22 | 0.28× | 38 / 86 | 28 / 86 | 2 / 6 |
| 2026-08-23 | 0.53× | 34 / 54 | 31 / 54 | 2 / 6 |
| 2026-08-24 | 0.41× | 63 / 70 | 54 / 67 | 2 / 4 |
| 2026-08-26 | 0.47× | 107 / 124 | 97 / 122 | 2 / 6 |
| 2026-08-27 | 0.44× | 156 / 159 | 131 / 153 | 2 / 6 |
| 2026-08-29 | 0.28× | 104 / 27 | 95 / 27 | 2 / 5 |
| 2026-09-02 | 0.46× | 8 / 12 | 5 / 10 | 2 / 4 |
| 2026-09-03 | 0.68× | 31 / 15 | 30 / 14 | 2 / 3 |
The measured pair page for these deployments: side-by-side cells. Downloads: ratio cells, value board, the rental prices these were costed at.