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

Cognitive State Tracking on User Fidelity Experiment Dataset

77.6E-A Score

CogWM-14B

Updated 26d ago

Evaluation Results

Method	Links
CogWM-14B 2026.06		77.6	77.3	70.5	45.8	29
GPT-5.5 2026.06		36.4	47.4	43.3	44.2	46
DS-V4-Pro 2026.06		31	46.2	44.5	41.2	52
Dual-LLM 2026.06		30.9	50	44.6	44.5	47
Qwen3-14B 2026.06		28.1	38.4	35.8	41.6	63
utt-only-14B 2026.06		12.2	28.5	34	26.4	-