Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Semantic Fidelity Evaluation on User Fidelity Experiment Dataset
Loading...
4.49
Emotion Fidelity Score (Emo)
CogWM-14B
2.0356
2.6728
3.31
3.9472
Jun 28, 2026
Emotion Fidelity Score (Emo)
Belief Fidelity Score (Bel)
Description Fidelity Score (Des)
Intent Fidelity Score (Int)
Utterance Fidelity Score (Utt)
Coherence Score (Coh)
Updated 26d ago
Evaluation Results
Method
Method
Links
Emotion Fidelity Score (Emo)
Belief Fidelity Score (Bel)
Description Fidelity Score (Des)
Intent Fidelity Score (Int)
Utterance Fidelity Score (Utt)
Coherence Score (Coh)
CogWM-14B
Parameter Count=14B, T...
2026.06
4.49
4.16
4.33
4.75
3.32
4.5
Qwen3-14B
Parameter Count=14B
2026.06
2.37
1.79
2.06
1.82
2.41
4.45
GPT-5.5
2026.06
2.34
1.9
2.09
1.74
2.62
4.71
utt-only-14B
Parameter Count=14B, T...
2026.06
2.22
1.24
1.17
1.31
1.13
2.43
DS-V4-Pro
2026.06
2.13
1.87
2.21
1.93
2.73
4.57
Dual-LLM
Backbone=GPT-5.5
2026.06
2.13
1.84
2.27
1.95
2.67
4.49
Feedback
Search any
task
Search any
task
