Same standard of work. About 5.0× the energy.
Claude Opus 4.8 scores higher than Claude Opus 4.1 on Epoch's Capabilities Index — 157.71 against 144.43, across 58 benchmarks covering coding, agents, long context and writing — while using about 5.0× less energy per answer. In blind head-to-head voting, people rate them 1461 and 1418 respectively.
| Claude Opus 4.8 | Claude Opus 4.1 | |
|---|---|---|
| Energy per answer | 18.4 Wh | 92.7 Wh |
| Same carbon as driving | 34 m | 171 m |
| Energy rank | 104 of 134 | 129 of 134 |
| Capability (science questions) | 91.0 | 73.2 |
| Epoch Capabilities Index | 157.71 | 144.43 |
| Human vote rating | 1461 | 1418 |
| Votes cast | 46,773 | 75,897 |
| Confidence | Day-one estimate | Day-one estimate |
| Released | 2026-05-28 | 2025-08-05 |
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 a science-question test; the Capabilities Index is a composite over 58 benchmarks; the vote rating comes from blind human comparisons. The full method is here.