RoleMRC
We show this table for reference; we do not rank on it.
Role-playing benchmark that checks whether a model keeps to a defined role identity while following instructions.
Benchmark score on RoleMRC — October 29, 2026
We compile the RoleMRC rows from provider self-reports. The table contains 2 models. Nemotron 3.5 Bolt E4B BF16 has the highest published score at 80.63%, 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 | 80.63% | Not reported | Open |
| 2 | Nemotron 3.5 Bolt E4BNVIDIA | 79.12% | 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 80.63%, which does not establish a market leader.
Honest limit: The stored score leaves out the multi-turn subset. Only NVIDIA-run results are stored so far, from one harness. Display-only and excluded from weighted ranking.
About RoleMRC
Year
2025
Tasks
Role-play and in-role instruction prompts
Format
LLM-judge average
Difficulty
Role identity adherence
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.
Freshness and provenance
Version
RoleMRC 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 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.
Compare top models on RoleMRC
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.