Expired60% confidenceFactTime unknown
OpenAI o4 scored 68.8% on the ARC-AGI-2 test, and GPT-5.2 scored 52.9%.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn the Terminal Bench 2.0 benchmark, OpenAI 4.6 scored 58% and GPT 5.4 scored 75.1%.71% similarUnverifiedThe o3 model achieved 87.5% on the ARC-AGI test in December 2024, and during the same period reached a rating of 2727 on Codeforces (surpassing 99.95% of human competitors).70% similarUnverifiedFable 5 scored 80.3 on the SWE Bench Pro programming test, while OpenAI's GPT 5.5 scored only 58.6.69% similarUnverifiedOpus 5在ARC-AGI 3上的得分是次优模型的三倍65% similarUnverifiedCodex 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.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/12518API
curl https://kongchang.com/api/v1/knowledge/claims/12518MCP
get_claim(id=12518)