# EQ-Bench 3

> Measures emotional intelligence in multi-turn roleplay scenarios, scored by an LLM judge against a rubric.

Canonical page: https://benchlm.ai/benchmarks/eqbench3

- Category: [Instruction Following](/instruction-following)
- Last updated: October 29, 2026

## About EQ-Bench 3

- Year: 2025
- Tasks: Multi-turn roleplay scenarios
- Format: LLM-judged rubric score
- Difficulty: Emotional and social intelligence
- Paper: [EQ-Bench 3](https://eqbench.com/eqbench3.html)

NVIDIA reports it for Nemotron 3.5 Bolt E4B (October 23, 2026), run in its NeMo Gym harness, as the rubric score with reasoning off. Rubric scores stay on this key, separate from the pairwise Elo scores on the EQ-Bench 4 board.

EQ-Bench 3 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (2 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Nemotron 3.5 Bolt E4B BF16](/models/nemotron-3-5-bolt-e4b-bf16) | NVIDIA | 39.40% |
| 2 | [Nemotron 3.5 Bolt E4B](/models/nemotron-3-5-bolt-e4b) | NVIDIA | 38.15% |

## FAQ

### What does EQ-Bench 3 measure?

Measures emotional intelligence in multi-turn roleplay scenarios, scored by an LLM judge against a rubric.

### Which model scores highest on EQ-Bench 3?

Nemotron 3.5 Bolt E4B BF16 by NVIDIA currently leads with a score of 39.40% on EQ-Bench 3.

### How many models are evaluated on EQ-Bench 3?

2 AI models have published results on EQ-Bench 3 in the BenchLM catalog.

### Does EQ-Bench 3 affect BenchLM's overall score?

Not directly. EQ-Bench 3 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on EQ-Bench 3

- [Nemotron 3.5 Bolt E4B BF16 vs Nemotron 3.5 Bolt E4B](/compare/nemotron-3-5-bolt-e4b-vs-nemotron-3-5-bolt-e4b-bf16)