Skip to content
Evaluation sources

EQ-Bench 4 · Emotional and interpersonal understanding

EQ-Bench · Assesses emotions, implicit needs, and communication preferences across multi-turn conversations.

Official evaluation
Across NexGateHub AI News Observing
Evidence budgetNot scored
Upstream data timeUnverified
Last successful syncCollection has not started

What it measures and how

Uses 120 simulated characters and 16 role-play turns, with three rotating blind model judges. Only Elo is used; behavioral traits are not higher-is-better ability scores. Old v3 results are not counted again.

How this evidence is used

Under review: public data and licensing are available, but a new evaluation is needed. The validity window is not extended to fill category coverage.

Evaluation limits & attribution

Simulated English conversations lack human-expert validation. They do not measure real satisfaction or Chinese emotional intelligence. Current results exceed the 45-day window.

Data license: MIT · Metadata declaration in the EQ-bench-site README.

Results are published by EQ-Bench. Original scores and the NexGateHub consensus index use different scales and cannot be added directly.