Expired60% confidenceFactTime unknown
Codex One's performance on SWE-bench is slightly better than O3 High, achieving an accuracy rate of 75% on OpenAI's internal software engineering tasks, compared to 70% for O3 High.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
OpenAI Codex Deep Dive: How Does the Async AI Coding Agent Actually Perform?
bilibiliKrillinAI小林
Related Entities
Related Claims
UnverifiedCodex One performs slightly better than O3 High on SWE-bench.78% similarUnverifiedIn programming benchmarks, Codex-1 outperformed Claude 3.7 and O3 High.72% similarUnverifiedIn the SWE-Bench score, o1 scored significantly higher than o3-mini medium but slightly lower than o3-mini-high.68% similarUnverifiedIn the AID benchmark, o1 high (corresponding to o1 pro) scored above 60 in programming ability, outperforming o3-mini-high, though the two are very close.66% similarUnverifiedOpenAI o4 scored 68.8% on the ARC-AGI-2 test, and GPT-5.2 scored 52.9%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4986API
curl https://kongchang.com/api/v1/knowledge/claims/4986MCP
get_claim(id=4986)