Unverified50% confidenceBenchmarkExact time
Scaling the model size by approximately one hundred thousand times improved the base LLM's score on ARC from only 0% to approximately 10%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
UnverifiedThe token conversion rate for advanced models is often 5 to 20 times higher than that of base models71% similarUnverifiedLRMs of comparable or even smaller scale have already saturated the ARC 1 benchmark, achieving accuracy close to 100%.71% similarUnverifiedThe performance of base LLMs on ARC 1 has to date remained at approximately 10%–15%.68% similarUnverifiedScale AI的研究团队发现，部分模型在被污染的基准上的表现比在新编写的同等难度题目上高出10-15个百分点66% similarUnverifiedThe power-law exponent between test loss and compute is approximately 0.05, meaning that every 10x increase in compute yields approximately a 12% improvement in model performance.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980203API
curl https://kongchang.com/api/v1/knowledge/claims/980203MCP
get_claim(id=980203)