Unverified50% confidenceBenchmarkExact time
The framework achieves an overall accuracy improvement of 6.9% over the current state of the art on the MERLIN benchmark.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEfficientNet 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%69% similarUnverifiedUnder the same model (Claude 4.6 Opus), OCR's precision is 33.9% versus 7.23% for the general-purpose agent, representing an approximately 4.7× improvement in precision.64% similarUnverifiedNCP-ArchPreview achieves a 5.99-point improvement on the mathematical reasoning benchmark GSM8K.63% 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62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907871API
curl https://kongchang.com/api/v1/knowledge/claims/907871MCP
get_claim(id=907871)