Expired85% confidenceFactTime unknown
GPT-5.4 achieved a score of 75% on the OS World Verified benchmark, surpassing the human baseline of 72.4% for the first time.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn standardized tests, GPT-4's performance has surpassed that of more than 90% of human test-takers.78% similarUnverifiedIn the DeepSWE benchmark, GPT 5.5 tops the leaderboard with a pass rate of approximately 70%, leading Opus 4.7 by more than 15 percentage points.78% similarVerifiedGPT-5.4 achieved 57.7% accuracy on SWE-Bench Pro, surpassing GPT-5.3-Codex's 56.8%.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/19302API
curl https://kongchang.com/api/v1/knowledge/claims/19302MCP
get_claim(id=19302)