Share your thoughts, 1 month free Claude Pro on usSee more

Vocabulary Difficulty Prediction on KVL data (test)

0.989PCC (Chinese)

Statistical Optimum

Updated 19d ago

Evaluation Results

Method	Links
Statistical Optimum 2026.05		0.989	0.99	0.995	0.991
finetuned_llms_plus 2026.05		0.928	0.915	0.919	0.921
open_max 2026.05		0.927	0.916	0.92	0.921
≤32B LLM Average 2026.05		0.926	0.914	0.916	0.918
finetuned_llms 2026.05		0.925	0.914	0.915	0.918
≤14B LLM Average 2026.05		0.921	0.905	0.908	0.911
GLM-4-32B 2026.05		0.918	0.907	0.906	0.91
Qwen2.5-32B 2026.05		0.917	0.902	0.907	0.909
≤9B LLM Average 2026.05		0.916	0.901	0.9	0.906
Ministral-3-14B 2026.05		0.915	0.902	0.907	0.908
closed_max 2026.05		0.874	0.844	0.854	0.857
explainable 2026.05		0.837	0.779	0.789	0.802
explainable 2026.05		0.82	0.768	0.776	0.788
explainable 2026.05		0.815	0.766	0.769	0.783
Open-Track Baseline 2026.05		0.804	0.786	0.783	0.791
traditional 2026.05		0.767	0.747	0.721	0.745
Closed-Track Baseline 2026.05		0.753	0.773	0.765	0.764