Expired50% confidenceFactTime unknown
Codex One performs slightly better than O3 High on SWE-bench.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
OpenAI Codex Deep Dive: How Does the Async AI Coding Agent Actually Perform?
bilibiliKrillinAI小林
Related Claims
UnverifiedCodex 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.78% similarUnverifiedIn programming benchmarks, Codex-1 outperformed Claude 3.7 and O3 High.76% similarUnverifiedIn the SWE-Bench score, o1 scored significantly higher than o3-mini medium but slightly lower than o3-mini-high.64% similarUnverifiedSW1E1's capabilities are close to the level of Claude 3.7 and Claude 3.5, and are notably better than DeepSeek V3.61% similarUnverifiedCodex Max outperforms the original GPT-5.1 Codex on the SWE-Bench validation set while reducing thinking tokens by 30%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/54738API
curl https://kongchang.com/api/v1/knowledge/claims/54738MCP
get_claim(id=54738)