Same standard of work. About 5.4× the energy.
Inkling-Small scores higher than o3 on Epoch's Capabilities Index — 150.15 against 146.91, across 58 benchmarks covering coding, agents, long context and writing — while using about 5.4× less energy per answer. In blind head-to-head voting, people rate them 1412 and 1410 respectively.
| Inkling-Small | o3 | |
|---|---|---|
| Energy per answer | 4.97 Wh | 26.6 Wh |
| Same carbon as driving | 9 metres | 49 metres |
| Energy rank | 176 of 266 | 238 of 266 |
| Capability (58 benchmarks) | 150.2 | 146.9 |
| Human vote rating | 1412 | 1410 |
| Votes cast | 18,844 | 58,579 |
| Confidence | Calculated | Inferred |
| Released | 2026-07-15 | 2025-04-16 |
Energy is calculated the same way for every model on this site, from public data and calibrated against laboratory measurement — accurate to roughly a factor of two to three, which is why we only ever state a difference of 5× or more. Capability is Epoch AI's Capabilities Index, one score combining 58 separate benchmarks; the vote rating comes from blind human comparisons. The full method is here.