Expired60% confidenceFactTime unknown
In an internal spreadsheet modeling test simulating a junior investment banking analyst, GPT-5.4 averaged 87.3%, while GPT-5.2 scored only 68.4%.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedGPT-5.5's score on the GPQA doctoral-level scientific reasoning benchmark improved from 78.5% to 85.6%.79% similarUnverifiedGPT-5.5's score on the AIME 2025 math competition improved from 65.4% to 81.2%.76% similarVerifiedGPT-5.4 achieved 57.7% accuracy on SWE-Bench Pro, surpassing GPT-5.3-Codex's 56.8%.75% similarUnverified测试者认为GPT-5.6相较于5.4和5.5是一次质变级别的提升74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/13759API
curl https://kongchang.com/api/v1/knowledge/claims/13759MCP
get_claim(id=13759)