# RoleBench leaderboard

Instruction Following benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/instruction-following-role-bench

RoleBench (RoleLLM). Every model the catalog carries a published RoleBench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Instruction Following |
| Measure | Win rate against reference responses |
| Tasks | Character role-play prompts |
| Difficulty | Character speaking style |
| Published by | [RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models](https://github.com/InteractiveNLP-Team/RoleLLM-public) |

Character role-play benchmark from the RoleLLM project that tests whether a model speaks in a given character's style.

## RoleBench ranking

2 models with a published RoleBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Win rate against reference responses | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Nemotron 3.5 Bolt E4B](https://modelchoice.dev/models/nemotron-3-5-bolt-e4b) | NVIDIA | 71.21 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Nemotron 3.5 Bolt E4B BF16](https://modelchoice.dev/models/nemotron-3-5-bolt-e4b-bf16) | NVIDIA | 67.05 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
