Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Instruction Following benchmark
RoleBench (RoleLLM). Every model the catalog carries a published RoleBench value for, ranked by that value.
Character role-play benchmark from the RoleLLM project that tests whether a model speaks in a given character's style. 2 models in the ModelChoice catalog have a published value.
Each point is a model with a published RoleBench value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
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 |
|---|---|---|---|
| 1 | NVIDIA | 71.21 | |
| 2 | NVIDIA | 67.05 |
Evidence key: Observed
Rows are ordered by the value RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
What the benchmark measures and how its value is published, from the source’s own record.
RoleBench (RoleBench (RoleLLM)) is an instruction following benchmark published by RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models. Character role-play benchmark from the RoleLLM project that tests whether a model speaks in a given character's style. Its evaluation set is described by the source as character role-play prompts. The source rates its difficulty as character speaking style.
Each model's result is published by RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models as win rate against reference responses. ModelChoice prints that value to 2 decimal places, exactly as published, and never converts or rescales it. This page ranks the 2 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
All leaderboards · Instruction Following capability leaderboard