FLAN 137B vs GPT-3.5 (davinci-002)

FLAN 137B (Google Research) and GPT-3.5 (davinci-002) (OpenAI) are both frontier AI models. FLAN 137B was published in September 2021 and GPT-3.5 (davinci-002) in March 2022.

GPT-3.5 (davinci-002) was trained on 2.6×10²⁴ FLOP, about 1.3x the compute of FLAN 137B at 2×10²⁴ FLOP. Training compute is the closest available proxy for how much was invested in a model, though it says nothing on its own about how well that compute was spent.

These two models share no benchmark on which both have been scored, so no direct performance comparison is possible here. The specification table below is a comparison of inputs, not of results.