# RoleMRC

> Role-playing benchmark that checks whether a model keeps to a defined role identity while following instructions.

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

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

## About RoleMRC

- Year: 2025
- Tasks: Role-play and in-role instruction prompts
- Format: LLM-judge average
- Difficulty: Role identity adherence
- Paper: [RoleMRC](https://github.com/LuJunru/RoleMRC)

NVIDIA reports it for Nemotron 3.5 Bolt E4B (October 23, 2026), run in its NeMo Gym harness, as the judge average excluding the multi-turn subset, in reasoning mode.

RoleMRC 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 | 80.63% |
| 2 | [Nemotron 3.5 Bolt E4B](/models/nemotron-3-5-bolt-e4b) | NVIDIA | 79.12% |

## FAQ

### What does RoleMRC measure?

Role-playing benchmark that checks whether a model keeps to a defined role identity while following instructions.

### Which model scores highest on RoleMRC?

Nemotron 3.5 Bolt E4B BF16 by NVIDIA currently leads with a score of 80.63% on RoleMRC.

### How many models are evaluated on RoleMRC?

2 AI models have published results on RoleMRC in the BenchLM catalog.

### Does RoleMRC affect BenchLM's overall score?

Not directly. RoleMRC is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on RoleMRC

- [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)