Expired85% confidenceFactTime unknown
Codex Max outperforms the original GPT-5.1 Codex on the SWE-Bench validation set while reducing thinking tokens by 30%.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
GPT-5.1 Pro Deep Dive: The Smartest AI Trapped in the Worst Interface
bilibili安得广厦千万间678
Related Entities
Related Claims
UnverifiedThe gap in resolution rate on SWE-Bench Verified between Claude Sonnet 4.6 and GPT-5.1 Codex is only 3.3 percentage points.68% similarUnverifiedIn the SWE-Bench evaluation, Claude Code scored 59 points and Codex scored 56.8 points.68% similarUnverifiedCodex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%65% similarUnverifiedCodex's thinking intensity is divided into four levels: low, medium, high, and ultra-high.65% similarUnverifiedThe original Codex achieved a pass@1 score of 28.8% on the HumanEval benchmark, whereas using GPT-3 directly yielded only 0%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/12478API
curl https://kongchang.com/api/v1/knowledge/claims/12478MCP
get_claim(id=12478)