Role-play Benchmark (MiniMax)
Doubao-1.5-pro 80.6 leads the models we track Role-play agents are tested on situated reenactment in Chinese and English scenes. Grading targets the immersive experience rather than a verifiable answer.
About 160 likes on Hugging Face.
- Made by
- MiniMax
- Released
- January 2026
- Kind
- Creative writing
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Strongest model tested
-
Gemini 3 Pro #55 on the capability index - Last model added
- December 2025
- Scores refreshed
- November 12th, 2026
MiniMax-M2-her tops the leaderboard with 84.7
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Doubao-1.5-pro, at 80.6.
The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
- Gemini 4 Carbon
- GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 MiniMax-M2-her 84.7
- 2 Doubao-1.5-pro 80.6
- 3 GPT-5.1 80.6
- 4 Claude Opus 4.5 high thinking 76.6
- 5 Gemini 3 Pro 75.6
- 6 Claude Sonnet 4.5 69.3
- 7 gemini-2.5-pro (snapshot unspecified) 68.2
- 8
DeepSeek-V3.1 64.2 - 9 DeepSeek-V3.2 60.3
- 10 Grok 4.1 48.5
Source: Official Role-play Benchmark (MiniMax) leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | MiniMax-M2-her | 84.7 | Official leaderboard | ||
| 2 | Doubao-1.5-pro | 80.6 | Jan 2025 | Official leaderboard | |
| 3 | GPT-5.1 | 80.6 | Nov 2025 | Official leaderboard | |
| 4 | Claude Opus 4.5 | 76.6 | high thinking | Nov 2025 | Official leaderboard |
| 5 | Gemini 3 Pro | 75.6 | Nov 2025 | Official leaderboard | |
| 6 | Claude Sonnet 4.5 | 69.3 | Sep 2025 | Official leaderboard | |
| 7 | gemini-2.5-pro (snapshot unspecified) | 68.2 | Official leaderboard | ||
| 8 | DeepSeek-V3.1 | 64.2 | Aug 2025 | Official leaderboard | |
| 9 | DeepSeek-V3.2 | 60.3 | Dec 2025 | Official leaderboard | |
| 10 | Grok 4.1 | 48.5 | Nov 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Role-play Benchmark (MiniMax) leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Role-play Benchmark (MiniMax) leaderboard
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Writing and taste
- Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
- WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
- Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing.
MiniMax-Text-01 81.3% - DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate. DeepSeek-V4-Pro 62.6%
- Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
- Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right.
Muse Spark 0.21