The AI Footprint ← All 266 models

Claude Opus 4.1 vs GPT-5.4

Same standard of work. About 11× the energy.

Use this
OpenAI
7.64 Wh
≈ 14 metres of driving
Instead of this
Anthropic
86.7 Wh
≈ 160 metres of driving

The verdict

GPT-5.4 scores higher than Claude Opus 4.1 on Epoch's Capabilities Index — 156.86 against 144.11, across 58 benchmarks covering coding, agents, long context and writing — while using about 11× less energy per answer. In blind head-to-head voting, people rate them 1470 and 1418 respectively.

Side by side

GPT-5.4Claude Opus 4.1
Energy per answer7.64 Wh86.7 Wh
Same carbon as driving14 metres160 metres
Energy rank200 of 266257 of 266
Capability (58 benchmarks)156.9144.1
Human vote rating14701418
Votes cast60,53775,913
ConfidenceDay-one estimateDay-one estimate
Released2026-03-052025-08-05

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 Epoch AI's Capabilities Index, one score combining 58 separate benchmarks; the vote rating comes from blind human comparisons. The full method is here.

Share this

Data built 2026-09-20 · Claude Opus 4.1 in detail · GPT-5.4 in detail · all 266 models · compare any two models yourself