Same standard of work. About 13× the energy.
Claude Sonnet 5.5 scores higher than Gemini 2.5 Pro (Mar 2025) on Epoch's Capabilities Index, 164.45 against 142.44, across 58 benchmarks covering coding, agents, long context and writing, while using about 13× less energy per answer. Claude Sonnet 5.5 has not faced human head-to-head voting, where Gemini 2.5 Pro (Mar 2025) carries 125,366 votes, worth weighing.
| Claude Sonnet 5.5 | Gemini 2.5 Pro (Mar 2025) | |
|---|---|---|
| Energy per answer | 5.64 Wh | 72.1 Wh |
| Carbon released | 2.6 g CO₂ | 33 g CO₂ |
| Same carbon as driving | 10 metres (34 feet) | 133 metres (436 feet) |
| Energy rank | 193 of 277 | 270 of 277 |
| Capability (58 benchmarks) | 164.4 | 142.4 |
| Human vote rating | - | 1458 |
| Votes cast | - | 125,366 |
| Confidence | Day-one estimate | Day-one estimate |
| Released | 2026-09-28 | 2025-03-31 |
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.