The AI Footprint ← All 136 models

GLM-5.1 vs GPT-5.4

Same standard of work. About 5.1× the energy.

Use this
OpenAI
7.94 Wh
≈ 15 metres of driving
Instead of this
Z.ai (Zhipu AI)
40.8 Wh
≈ 75 metres of driving

The verdict

GPT-5.4 scores higher than GLM-5.1 on Epoch's Capabilities Index — 156.86 against 149.71, across 58 benchmarks covering coding, agents, long context and writing — while using about 5.1× less energy per answer. In blind head-to-head voting, people rate them 1470 and 1462 respectively.

Side by side

GPT-5.4GLM-5.1
Energy per answer7.94 Wh40.8 Wh
Same carbon as driving15 metres75 metres
Energy rank92 of 136117 of 136
Capability (science questions)93.389.9
Epoch Capabilities Index156.86149.71
Human vote rating14701462
Votes cast60,53748,901
ConfidenceDay-one estimateDay-one estimate
Released2026-03-052026-04-07

What these figures are

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.

Share this

Data built 2026-09-14 · GLM-5.1 in detail · GPT-5.4 in detail · all 136 models · compare any two models yourself