# Multimodal emotion recognition on MER-UniBench (official)

Source: [Multimodal emotion recognition on MER-UniBench (official)](<https://www.sota2.com/research/sota/multimodal-emotion-recognition-on-mer-unibench-official>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-29T06:44:51.853Z

Evaluation of Multimodal Emotion Recognition performance on the official split of the MER-UniBench dataset, reporting the Mean score.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Multimodal emotion recognition |
| Dataset (including any stated split) | MER-UniBench (official) |
| Metric | Mean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Mean Accuracy](<https://www.sota2.com/research/sota/multimodal-emotion-recognition-on-mer-unibench-official.md?metric=Mean%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Mean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MER-R1 | 83.5 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| AffectGPT-R1 | 79.98 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| Baseline | 77.87 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| AffectGPT-R1 | 75.6 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| AffectGPT | 74.77 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| AffectGPT | 71.96 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| Emotion-LLaMA | 64.17 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| mPLUG-Owl | 62.45 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| R1-Omni | 59.61 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| Chat-UniVi | 57.94 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| SALMONN | 57.89 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| LLaMA-VID | 56.07 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| PandaGPT | 52.92 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| VideoChat2 | 52.67 | Not recorded | 6a41fc1f206542251d7ccbb1 |
| Qwen-Audio | 49.26 | Not recorded | 6a41fc1f206542251d7ccbb1 |

### MER-R1

Mean Accuracy: 83.5. Result ID: 6a42145cfbc373592c86a307.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AffectGPT-R1

Mean Accuracy: 79.98. Result ID: 6a42145cfbc373592c86a303.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a531e209131cea827a6.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Baseline

Mean Accuracy: 77.87. Result ID: 6a42145cfbc373592c86a306.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AffectGPT-R1

Mean Accuracy: 75.6. Result ID: 6a42145cfbc373592c86a305.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a531e209131cea827a6.md>)

Recorded evaluation configuration: {"Reproduced":"true"}. This record does not assert independent reproduction.

### AffectGPT

Mean Accuracy: 74.77. Result ID: 6a42145cfbc373592c86a302.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78621e209131cea781ae.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AffectGPT

Mean Accuracy: 71.96. Result ID: 6a42145cfbc373592c86a304.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78621e209131cea781ae.md>)

Recorded evaluation configuration: {"Reproduced":"true"}. This record does not assert independent reproduction.

### Emotion-LLaMA

Mean Accuracy: 64.17. Result ID: 6a42145cfbc373592c86a301.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75901e209131cea68a90.md>)

[Implementation](<https://github.com/ZebangCheng/Emotion-LLaMA>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### mPLUG-Owl

Mean Accuracy: 62.45. Result ID: 6a42145cfbc373592c86a2fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ae1e209131cea57d83.md>)

[Implementation](<https://github.com/X-PLUG/mPLUG-Owl>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### R1-Omni

Mean Accuracy: 59.61. Result ID: 6a42145cfbc373592c86a300.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa775e1e209131cea72c53.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Chat-UniVi

Mean Accuracy: 57.94. Result ID: 6a42145cfbc373592c86a2fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d31e209131cea58bff.md>)

[Implementation](<https://github.com/PKU-YuanGroup/Chat-UniVi>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SALMONN

Mean Accuracy: 57.89. Result ID: 6a42145cfbc373592c86a2fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d71e209131cea58d8a.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### LLaMA-VID

Mean Accuracy: 56.07. Result ID: 6a42145cfbc373592c86a2fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea50559.md>)

[Implementation](<https://github.com/dvlab-research/LLaMA-VID>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PandaGPT

Mean Accuracy: 52.92. Result ID: 6a42145cfbc373592c86a2ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea46009.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VideoChat2

Mean Accuracy: 52.67. Result ID: 6a42145cfbc373592c86a2fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73411e209131cea5b4b7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Qwen-Audio

Mean Accuracy: 49.26. Result ID: 6a42145cfbc373592c86a2f9.

[Reporting paper](<https://www.sota2.com/research/paper/6a41fc1f206542251d7ccbb1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c5b.md>)

[Implementation](<https://github.com/QwenLM/Qwen-Audio>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
