EQ-Bench 3
We show this table for reference; we do not rank on it.
Measures emotional intelligence in multi-turn roleplay scenarios, scored by an LLM judge against a rubric.
Benchmark score on EQ-Bench 3 — October 29, 2026
We compile the EQ-Bench 3 rows from provider self-reports. The table contains 2 models. Nemotron 3.5 Bolt E4B BF16 has the highest published score at 39.40%, but the available coverage and evaluation setups do not establish a market leader. We do not use these results to rank models overall.
Nemotron 3.5 Bolt E4B BF16
NVIDIA
Nemotron 3.5 Bolt E4B
NVIDIA
2 modelsInstruction FollowingCurrentDisplay onlyUpdated October 29, 2026
Benchmark score table (2 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Nemotron 3.5 Bolt E4B BF16NVIDIA | 39.40% | Not reported | Open |
| 2 | Nemotron 3.5 Bolt E4BNVIDIA | 38.15% | Not reported | Open |
How to read this leaderboard
Operator receipt: 2 sourced rows are currently displayable on this page; the highest published score among these 2 models is Nemotron 3.5 Bolt E4B BF16 at 39.40%, which does not establish a market leader.
Honest limit: Scores depend on the judge model and rubric version. Only NVIDIA-run results are stored so far, from one harness. Display-only and excluded from weighted ranking.
About EQ-Bench 3
Year
2025
Tasks
Multi-turn roleplay scenarios
Format
LLM-judged rubric score
Difficulty
Emotional and social intelligence
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.
Freshness and provenance
Version
EQ-Bench 3 2025
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
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.
Compare top models on EQ-Bench 3
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 6,100+ subscribers.
One email each week. Unsubscribe anytime.