Same standard of work. About 8.2× the energy.
Grok 4.7 scores higher than MiniMax-M2.7 on Epoch's Capabilities Index, 154.37 against 145.88, across 58 benchmarks covering coding, agents, long context and writing, while using about 8.2× less energy per answer. Grok 4.7 has not faced human head-to-head voting, where MiniMax-M2.7 carries 84,977 votes, worth weighing.
| Grok 4.7 | MiniMax-M2.7 | |
|---|---|---|
| Energy per answer | 0.285 Wh | 2.34 Wh |
| Carbon released | 0.13 g CO₂ | 1.1 g CO₂ |
| Same carbon as driving | under a metre | 4 metres (14 feet) |
| Energy rank | 21 of 277 | 160 of 277 |
| Capability (58 benchmarks) | 154.4 | 145.9 |
| Human vote rating | - | 1405 |
| Votes cast | - | 84,977 |
| Confidence | Calculated | Inferred |
| Released | 2026-09-21 | 2026-03-18 |
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.