Unverified50% confidenceBenchmarkExact time
In the hard-to-verify category with no bait, GPT-5.4 nano answered only 19/40 questions correctly in both orderings and had a 65% probability of selecting Response A; GPT-5.4 mini had a 66% probability of selecting A, Grok 4.20 non-reasoning was 62%, while strong judges were stable at 50%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedIn the hard-to-verify category with injection bait, the number of questions for which GPT-5.4 mini judged incorrectly in both orderings rose from 3 to 39, Qwen3-Next 80B Instruct from 4 to 38, and GPT-5.4 mini and Qwen3-Next Instruct scored zero on hard questions (below the approximately 0.25 expected from random coin flipping).72% similarUnverifiedIn CAD World's 200-task evaluation, the best-performing GPT-5.4 achieved a success rate of only 17.5%.69% 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%.68% similarUnverifiedGPT-5.4 has an accuracy of 50.5%, while its paired always-predict-up baseline is 51.6%.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/996775API
curl https://kongchang.com/api/v1/knowledge/claims/996775MCP
get_claim(id=996775)