Unverified50% confidenceBenchmarkExact time
After full pretraining, NCP-ArchPreview outperforms OLMo-3-7B by 2.45 points on the macro-average score across downstream tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedNCP-ArchPreview achieves the final pretraining loss of OLMo-3-7B while consuming only 51.3% of the training tokens.75% similarUnverifiedNCP-ArchPreview achieves a 5.99-point improvement on the mathematical reasoning benchmark GSM8K.57% similarUnverifiedIn the DistilBERT-to-DistilBERT configuration on the SST-2 dataset, the reliability-gated method achieved 88.800±0.532%, RAPID achieved 88.685±0.462%, both improving approximately 1.4 percentage points over the baseline of 87.271±0.162%57% similarUnverifiedEfficientNet 从 B0 到 B7，模型参数从 5.3M 增长到 66M，Top-1 精度从 77.1% 提升到 84.3%56% similarUnverifiedClaude achieved a task completion rate of 14.9% on the OSWorld benchmark, representing the highest level at the time.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907844API
curl https://kongchang.com/api/v1/knowledge/claims/907844MCP
get_claim(id=907844)