TAG
#GPT
2026-05 1 post
-
10 OpenAI Models Through Quick Benchmarks — The Model Isn't as Smart as You Pay
19 configurations of 10 OpenAI models, 30 runs each on three reasoning problems. gpt-5-nano on minimal scored 4.4%; o1 scored 47.8%, below gpt-4o at 66.7%.
No matching posts.