Falcon-180B (Technology Innovation Institute) and GPT-4 (Jun 2023) (OpenAI) are both frontier AI models. Falcon-180B was published in September 2023 and GPT-4 (Jun 2023) in June 2023.
GPT-4 (Jun 2023) was trained on 2.1×10²⁵ FLOP, about 5.6x the compute of Falcon-180B at 3.8×10²⁴ 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.
GPT-4 (Jun 2023) wins the single benchmark both were scored on. Benchmark counts are a crude scoreboard — the evaluations differ wildly in what they measure and in how saturated they are — so the per-benchmark table below matters more than the tally.
