On the HumanEval coding benchmark, GPT-3.5 with zero-shot prompting achieves 48% accuracy, GPT-4 achieves 67% accuracy, but GPT-3.5 wrapped in an agentic workflow actually outperforms GPT-4, and an agentic workflow around GPT-4 performs even better.

factualpending

Speaker

Andrew Ng

Evidence Quote

“if you use GPT 3.5 uh zero shot prompting it gets it 48% right uh gp4 way better 607 7% right but if you take an agentic workflow and wrap it around GPT 3.5 I say it actually does better than even gbd4”

Source

What's next for AI agentic workflows ft. Andrew Ng of AI Fund— Sequoia Capital
Created: 8/11/2026, 1:37:51 AM

Your notes

Loading notes...