Unverified50% confidenceBenchmarkExact time
In an editing benchmark, the same GPT model's score dropped from 99% to 70% depending on the framework used.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTaking GPT-MoE as an example, if the total number of experts is 64 and each token only activates Top-2, the actual computation can be reduced by approximately 97% compared to a Dense model of equivalent scale77% similarUnverified一项针对GPT-4的研究显示，对MMLU题目进行语义等价改写后，模型准确率在部分子集上下降超过10个百分点74% similarUnverifiedIn 96% of levels, GPT-6 required fewer attempts to find the answer than the average person.74% similarUnverifiedGPT-6 Astra achieved a near-perfect score of 99.9% on ARC-AGI-type tests, while the average score of ordinary human test-takers was only 48%.72% similarUnverifiedIn an unknown-rules mini-game test designed specifically for models, GPT-6 scored 99 points, approaching a perfect score, while the highest human score was only in the 30s and other models scored around 40.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987301API
curl https://kongchang.com/api/v1/knowledge/claims/987301MCP
get_claim(id=987301)