Unverified50% confidenceBenchmarkExact time
Under the optimal configuration, the EduBehaviors framework achieves a macro F1 score of 0.673 and a Cohen's kappa of 0.688.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOllama Hub hosts a variety of models ranging from 7B to 70B parameters.66% similarUnverifiedThe CAPI-DINO ViT-B/14 model achieved a linear probing accuracy of 68.7% on the iNat21 dataset.64% similarUnverified在MoE模型中每个token只激活少量Expert（通常2-4个，Top-K路由），实际计算量可能仅相当于6-7B的Dense模型61% similarUnverifiedThe best-performing Edu-QuRater achieved an average accuracy of 0.917 in reproducing GPT-4.1-mini pairwise judgments on the held-out set.61% similarVerifiedThe larger the number of model parameters, the greater the robustness to quantization, allowing 70B-level models to maintain performance close to FP16 after 4-bit quantization.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946236API
curl https://kongchang.com/api/v1/knowledge/claims/946236MCP
get_claim(id=946236)