Unverified60% confidenceBenchmarkExact time

Early GPT-3's HumanEval Pass@1 was below 10%, while top models such as GPT-4o and Claude 3.5 Sonnet have now consistently exceeded 85%.

2

Sources

60%

Confidence

Medium-term (~90 days)

Relevance

7/21/2026

First Seen

Valid until: 10/19/2026(expired)

Sources

Vibe Coding: A Beginner's Guide to Building Software with AI — No Coding Required

Related Claims

VerifiedGPT-4 and Claude 3 achieve pass@1 rates exceeding 85% on the HumanEval code benchmark.81% similar UnverifiedEven the most advanced current models such as GLM-5.2, Claude-Sonnet-4.6, and GPT achieve only just over half marks on this benchmark.77% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/584928

API

curl https://kongchang.com/api/v1/knowledge/claims/584928

MCP

get_claim(id=584928)