Unverified50% confidenceBenchmarkExact time
NCP-ArchPreview achieves a 5.99-point improvement on the mathematical reasoning benchmark GSM8K.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
VerifiedChain-of-Thought prompting improved PaLM 540B's accuracy on the GSM8K math benchmark from 17.9% to 58.1%.70% similarUnverified在 GSM8K 基准上，标准思维链准确率约为 56%-63%（GPT-3 规模），PAL 可提升至 72% 以上64% similarUnverifiedBlackwell架构FP4矩阵乘法理论峰值算力相比FP16提升可达8倍64% similarUnverifiedThe framework achieves an overall accuracy improvement of 6.9% over the current state of the art on the MERLIN benchmark.63% similarUnverifiedNVFP4量化方案相比BF16基线实现了1.5倍的推理加速，同时在top-1准确率上保留了92%到97%的水平63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907845API
curl https://kongchang.com/api/v1/knowledge/claims/907845MCP
get_claim(id=907845)