What it measures

Evaluates emotional intelligence, interpersonal nuance, theory of mind, and non-slop literary prose quality.

Reading the measurement

A preference result depends on the opponents, judges and prompts in the comparison pool. Use it to study which outputs people or judges favor, then check correctness and reliability with a separate task-based evaluation. Ratings from different arenas do not share a universal scale.

Published evaluation

Native original EQ-Bench score. Version 3 and the Creative Writing Arena use distinct protocols and must not be inferred from these numbers.

Where this fits in an evaluation suite

Format compliance, preference, truthfulness, and safety require separate measurements. Keep desirable writing style from masking factual errors.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Native original EQ-Bench score. Version 3 and the Creative Writing Arena use distinct protocols and must not be inferred from these numbers.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models — published result table ↗

    Paech, Samuel J. · 2023

Reviewed 2026-10-27. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.