Same standard of work. About 63× the energy.
Qwen3.6 27B scores higher than MiniMax-M3 on Epoch's Capabilities Index — 146.49 against 146.47, across 58 benchmarks covering coding, agents, long context and writing — while using about 63× less energy per answer. Qwen3.6 27B has not faced human head-to-head voting, where MiniMax-M3 carries 48,540 votes — worth weighing.
| Qwen3.6 27B | MiniMax-M3 | |
|---|---|---|
| Energy per answer | 0.351 Wh | 22.0 Wh |
| Same carbon as driving | under a metre | 41 metres |
| Energy rank | 38 of 136 | 112 of 136 |
| Capability (science questions) | 84.8 | 90.9 |
| Epoch Capabilities Index | 146.49 | 146.47 |
| Human vote rating | — | 1433 |
| Votes cast | — | 48,540 |
| Confidence | Calculated | Calculated |
| Released | 2026-04-22 | 2026-06-01 |
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.