The AI Footprint ← All 134 models

Gemini 2.5 Pro (Mar 2025) vs GPT-5.4

Same standard of work. About 10.0× the energy.

Use this
OpenAI
7.94 Wh
≈ 15 m of driving
Instead of this
Google DeepMind
79.3 Wh
≈ 146 m of driving

The verdict

GPT-5.4 scores higher than Gemini 2.5 Pro (Mar 2025) on Epoch's Capabilities Index — 156.4 against 145.59, across 58 benchmarks covering coding, agents, long context and writing — while using about 10.0× less energy per answer. In blind head-to-head voting, people rate them 1470 and 1458 respectively.

Side by side

GPT-5.4Gemini 2.5 Pro (Mar 2025)
Energy per answer7.94 Wh79.3 Wh
Same carbon as driving15 m146 m
Energy rank91 of 134126 of 134
Capability (science questions)93.383.8
Epoch Capabilities Index156.4145.59
Human vote rating14701458
Votes cast60,614122,589
ConfidenceDay-one estimateDay-one estimate
Released2026-03-052025-03-31

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 2026-09-02 · Gemini 2.5 Pro (Mar 2025) in detail · GPT-5.4 in detail · all 134 models · compare any two models yourself