Expired70% confidenceFactTime unknown
GPT-5.5's score on the AIME 2025 math competition improved from 65.4% to 81.2%.
1
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
6/3/2026
First Seen
Valid until: 9/1/2026(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%.81% similarUnverifiedTesters consider GPT-5.6 to be a qualitative leap forward compared to 5.4 and 5.5.78% similarUnverifiedIn 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%.76% similarUnverifiedGPT 5.5 achieved a score of 87% on the TerminalBench 2.0 benchmark, significantly leading and surpassing Anthropic's yet-to-be-released Mythos model.74% similarUnverifiedGPT-5.6's coding capability reached 91.9% on key benchmarks and its safety evaluation CyberGym score reached 85.6%, both surpassing competitor Nexus 5.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/39255API
curl https://kongchang.com/api/v1/knowledge/claims/39255MCP
get_claim(id=39255)