---
title: "GLM 5.3 Flash on Role-Play Bench — SociaBench"
description: "Platform evaluation of GLM 5.3 Flash on Role-Play Bench: Overall 69.52 (out of 100), with scores by dimension, sample counts and evaluation times."
canonical: "https://sociabench.com/models/minimax-rp/glm-5-3-flash-260828"
markdown: "https://sociabench.com/models/minimax-rp/glm-5-3-flash-260828.md"
type: "WebPage / Dataset"
entity: "https://sociabench.com/models/minimax-rp/glm-5-3-flash-260828#evaluation"
about: "https://sociabench.com/b/minimax-rp#benchmark"
part_of: "https://sociabench.com/b/minimax-rp#leaderboard"
publisher: "SociaBench"
language: "en-US"
date_modified: "2026-11-02T02:04:06.732Z"
data_version: "all:23-1793585046732-r1793034246936-p2710 zh:23-1793585046732-r1793034246936-p2710 en:23-1793585046732-r1793034246936-p2710"
result_source: "Platform evaluation (Platform reproduction result)"
license: "https://sociabench.com/data-terms"
sources:
  - "Original source: MiniMax, Released January 2026 with the MiniMax-M2-her blog post, \"A Deep Dive into the MiniMax-M2-her\": https://www.minimax.io/news/a-deep-dive-into-the-minimax-m2-her-2"
  - "Test set and official implementation: https://huggingface.co/datasets/MiniMaxAI/role-play-bench"
  - "Reproduction report (SociaBench): https://sociabench.com/b/minimax-rp/methodology"
---

# GLM 5.3 Flash (260828) · Role-Play Bench

Results of GLM 5.3 Flash on [Role-Play Bench](https://sociabench.com/b/minimax-rp). Results SociaBench obtained on this platform by running the full test set under the benchmark's current reproduction protocol. Only these results are ranked.

## Results

| View | Rank | Overall | 95% CI | Samples | Model version | Evaluated at | Data version |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Overall | 12 / 12 | 69.52 | [68.93, 70.09] | 285 | — | 2026-11-02T02:04Z | 23-1793585046732-r1793034246936-p2710 |
| Chinese | 12 / 12 | 68.46 | [67.67, 69.32] | 150 | — | 2026-11-02T02:04Z | 23-1793585046732-r1793034246936-p2710 |
| English | 12 / 12 | 70.69 | [69.85, 71.51] | 135 | — | 2026-11-02T02:04Z | 23-1793585046732-r1793034246936-p2710 |

## Scores by group

| View | Worlds | Stories | Preferences |
| --- | --- | --- | --- |
| Overall | 56.25 | 74.68 | 90.90 |
| Chinese | 55.71 | 73.49 | 88.96 |
| English | 56.86 | 76.01 | 93.06 |

## Scores by dimension

| View | Basics | Logic | Knowledge | Diversity | Content Logic | Interaction |
| --- | --- | --- | --- | --- | --- | --- |
| Overall | 46.07 | 23.86 | 98.82 | 64.88 | 94.28 | 90.90 |
| Chinese | 45.00 | 23.07 | 99.05 | 63.11 | 94.24 | 88.96 |
| English | 47.26 | 24.74 | 98.57 | 66.85 | 94.33 | 93.06 |

## Sources and methods

- Original source: MiniMax, Released January 2026 with the MiniMax-M2-her blog post, "A Deep Dive into the MiniMax-M2-her": https://www.minimax.io/news/a-deep-dive-into-the-minimax-m2-her-2
- Test set and official implementation: https://huggingface.co/datasets/MiniMaxAI/role-play-bench
- Reproduction report (SociaBench): https://sociabench.com/b/minimax-rp/methodology
- Leaderboard: https://sociabench.com/b/minimax-rp

## Citation

If you repost or cite any evaluation result from this site, credit "SociaBench (AI Social Intelligence Leaderboards)" and link to this site: https://sociabench.com/models/minimax-rp/glm-5-3-flash-260828.