Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified60% confidenceBenchmarkExact time

初代Codex在HumanEval基准测试上的pass@1指标达到28.8%，而直接使用GPT-3仅为0%

2

Sources

60%

Confidence

Long-term

Relevance

7/12/2026

First Seen

Sources

国内直连Codex配置教程：GPT Agent完整上手指南

bilibili无汁西瓜6/26/2026

Related Claims

UnverifiedCodex于2021年发布时在HumanEval基准上达到28.8%的pass@1得分，而GPT-4在同一基准上已超过67%83% similar VerifiedCodex在HumanEval基准测试上达到了28.8%的pass@1准确率76% similar Unverified初版 Codex 采用约120亿参数规模，在 HumanEval 基准测试中达到 28.8% 的 pass@1 通过率68% similar Unverified在 SWE-bench 测试中，早期 GPT-4 解决率不足 2%，而 Claude 3.5 Sonnet 突破 49%66% similar UnverifiedClaude Sonnet 4.6与GPT-5.1 Codex在SWE-Bench Verified上的解决率差距仅为3.3个百分点64% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/488714

API

curl https://kongchang.com/api/v1/knowledge/claims/488714

MCP

get_claim(id=488714)