The AI Footprint ← All 134 models

GPT-4 Turbo (Nov 2023) vs Inkling-Small

Same standard of work. About 5.3× the energy.

Use this
Thinking Machines
4.97 Wh
≈ 9 m of driving
Instead of this
OpenAI
26.5 Wh
≈ 49 m of driving

The verdict

Inkling-Small scores higher than GPT-4 Turbo (Nov 2023) on Epoch's Capabilities Index — 150.19 against 126.2, across 58 benchmarks covering coding, agents, long context and writing — while using about 5.3× less energy per answer. In blind head-to-head voting, people rate them 1414 and 1271 respectively.

Side by side

Inkling-SmallGPT-4 Turbo (Nov 2023)
Energy per answer4.97 Wh26.5 Wh
Same carbon as driving9 m49 m
Energy rank78 of 134114 of 134
Capability (science questions)88.542.4
Epoch Capabilities Index150.19126.2
Human vote rating14141271
Votes cast13,43898,114
ConfidenceCalculatedDay-one estimate
Released2026-07-152024-01-25

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 · GPT-4 Turbo (Nov 2023) in detail · Inkling-Small in detail · all 134 models · compare any two models yourself