Expired60% confidenceBenchmarkExact time
GPT-5.6 set a new all-time high score of 53.6 on the Agent's Last Exam benchmark, surpassing Claude Opus 4.5 by 13.1 points.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/13/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/11/2026(expired)
Sources
GPT-5.6发布：三款模型对标Claude，ChatGPT Work超级应用全解析
bilibiliAI-seeker7/9/2026
Related Claims
VerifiedIn the Agents' Last Exam benchmark, GPT-5.6 Sol achieved a score of 53.6, which is 13.1 points higher than Claude Fable 5 using adaptive reasoning.82% similarUnverifiedIn the long-cycle agentic workflow test (Engines Last Exam), GPT-5.6 Sol scored 53.6, outperforming Faber-5 by 13.1 points.81% similarUnverifiedIn EvoArena testing, GPT-5.5, which achieved the highest Step Level score, had an accuracy of just over 50%, while Gemini-3.1 Pro and GLM-5.1, which performed best at the Chain Level, reached only approximately 28%–29%.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501552API
curl https://kongchang.com/api/v1/knowledge/claims/501552MCP
get_claim(id=501552)