Datasets·AI·human_vs_gpt4o_3lens

Human vs GPT-4o (Eval 17)

Human vs GPT-4o (3-lens) . PsyProxy quantitative evaluation. The excerpts reflect a diverse array of themes centered around **communication**, **relationships**, and **personal growth**. Many texts explore the intricacies of **social dynamics**, offering strategies for navigating situations like overcoming awkwardness, setting boundaries, and managing expectations. The tone is often conversational and supportive, with a focus on **self-improvement** and **emotional intelligence**. Recurring topics include the importance of **active listening**, establishing **boundaries**, and the complexities of interpersonal interactions, whether in friendships or romantic relationships. Additionally, there are reflections on **self-care** and the pursuit of personal passions, emphasizing the balance between individual needs and those of others. [Summary on 50 random texts by ChatGPT 4o Mini].

Distribution of Human vs GPT-4o
1
2
3,014 at floor2,664 at ceiling
5,678
items
1,136
holdout n
Human vs GPT-4o
target
Binary
kind
15
systems compared
Criterion validity

Reported holdout systems from the verified card

Binary classification uses FVE as the task-primary metric. Secondary columns keep the companion metrics visible so binary, ordinal, regression, and multiclass cards are not compared through one flattened score.

Model-family mix
PsyProxy · 4Baseline · 11
SystemFamilyVariantFVEAUCF1Primary scale
psyproxyPsyProxy — Technology Lens v0.5 · 800d
PsyProxypermissive0.9550.9990.987
psyproxyPsyProxy — Behavioral Sciences Lens v0.5 · 1000d
PsyProxypermissive0.9330.9990.982
psyproxyPsyProxy — Health Lens v0.9 · 1100d
PsyProxypermissive0.9310.9990.982
psyproxyPsyProxy — Sociology Lens v0.5 · 1000d
PsyProxypermissive0.9190.9980.979
baselineIMDB movie reviews (ACL) binary · via best lens
Baselinepermissive
baselineDisneyland TripAdvisor reviews binary · via best lens
Baselinepermissive
baselineDisneyland TripAdvisor reviews continuous · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews binary · via best lens
Baselinepermissive
baselineDouban movie reviews (Chinese) ordinal · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews continuous · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews ordinal · via best lens
Baselinepermissive
baselineSentiment140 tweets binary · via best lens
Baselinepermissive
baselineDruglib drug reviews regression · via best lens
Baselinepermissive
baselineLIAR fact-check statements ordinal · via best lens
Baselinepermissive
baselineDruglib drug reviews ordinal · via best lens
Baselinepermissive