reasoning benchmark
EQ-Bench
EQ-Bench is an LLM-judged test evaluating active emotional intelligence abilities, understanding, insight, empathy, and interpersonal skills. The test set contains 45 challenging roleplay scenarios, most of which constitute pre-written prompts spanning 3 turns. The benchmark evaluates the performance of models by validating responses against several criteria and conducts pairwise comparisons to report a normalized Elo computation for each model.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
EQ-Bench Ranking
Higher score ranks better on this benchmark.
| 1 | XA | 1,586 points | 100.0% | 2 | C | |
| 2 | XA | 1,585 points | 0.0% | 2 | C |
EQ-Bench Score Distribution
A closer view of the leading scores on this benchmark.
EQ-Bench Highlights
The leading models and scores on this benchmark.
What is EQ-Bench?
What EQ-Bench measures and how its scores work.
EQ-Bench is an LLM-judged test evaluating active emotional intelligence abilities, understanding, insight, empathy, and interpersonal skills. The test set contains 45 challenging roleplay scenarios, most of which constitute pre-written prompts spanning 3 turns. The benchmark evaluates the performance of models by validating responses against several criteria and conducts pairwise comparisons to report a normalized Elo computation for each model.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- EQ-Bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- eq-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about EQ-Bench.
Which model scores highest on EQ-Bench?
Grok-4.1 Thinking is currently ranked first with 1,586 points.
What does EQ-Bench measure?
EQ-Bench is an LLM-judged test evaluating active emotional intelligence abilities, understanding, insight, empathy, and interpersonal skills. The test set contains 45 challenging roleplay scenarios, most of which constitute pre-written prompts spanning 3 turns. The benchmark evaluates the performance of models by validating responses against several criteria and conducts pairwise comparisons to report a normalized Elo computation for each model.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.