Unverified50% confidenceBenchmarkExact time
开发效率维度Claude Code得9.8分，Codex得5.5分
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/22/2026
First Seen
Valid until: 11/20/2026
Sources
Related Entities
Related Claims
VerifiedClaude Sonnet 5 scores 63.22% on SWE-bench Verified (Agentic Coding), approximately 6 percentage points behind Opus 4.8.67% similarUnverifiedClaude Code + DeepSeek scored 100 points in stability testing, while Codex + DeepSeek scored only 40 points.66% similarUnverifiedIn recent hands-on tests, Codex has surpassed Claude Code in multiple evaluation dimensions.66% similarUnverifiedIn the SWE-Bench evaluation, Claude Code scored 59 points and Codex scored 56.8 points.66% similarUnverifiedMultiple independent benchmark tests consistently show that the token consumption ratio between Claude Code and Codex is between 3.2x and 4.2x.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/788311API
curl https://kongchang.com/api/v1/knowledge/claims/788311MCP
get_claim(id=788311)