# Textual Emotion Analysis on DFEC 2000 (test)

Source: [Textual Emotion Analysis on DFEC 2000 (test)](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test>)

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

Data updated: 2026-04-06T07:15:01.930Z

Evaluation of Textual Emotion Analysis performance on the test split of the DFEC 2000 dataset, reporting metrics including VideoChatGPT Score, Correctness, Detail, Context, Temporal, CIDEr, Rouge-L, and AutoDQ.

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 | Textual emotion analysis |
| Dataset (including any stated split) | DFEC 2000 (test) |
| Metric | VideoChatGPT Score (Overall) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 28 of 28 |
| 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

- [VideoChatGPT Score (Overall)](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=VideoChatGPT%20Score%20(Overall)>): Higher is better; unit: SCALAR.

- [Correctness](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=Correctness>): Higher is better; unit: SCALAR.

- [Detail](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=Detail>): Higher is better; unit: SCALAR.

- [Context](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=Context>): Higher is better; unit: SCALAR.

- [Temporal](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=Temporal>): Higher is better; unit: SCALAR.

- [CIDEr](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=CIDEr>): Higher is better; unit: PERCENT.

- [Rouge-L](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=Rouge-L>): Higher is better; unit: PERCENT.

- [AutoDQ](<https://www.sota2.com/research/sota/textual-emotion-analysis-on-dfec-2000-test.md?metric=AutoDQ>): Higher is better; unit: PERCENT.

## Recorded results

| Method | VideoChatGPT Score (Overall) | Result date | Report paper |
| --- | --- | --- | --- |
| FaVChat-Qwen3 | 9.01 | Not recorded | 68fa77611e209131cea72d93 |
| FaVChat-Qwen2.5 | 8.89 | Not recorded | 68fa77611e209131cea72d93 |
| Qwen3-VL-8B-Face | 8.87 | Not recorded | 68fa77611e209131cea72d93 |
| Qwen2.5-VL-7B-Face | 8.64 | Not recorded | 68fa77611e209131cea72d93 |
| Qwen2.5-VL-72B | 8.47 | Not recorded | 68fa77611e209131cea72d93 |
| Qwen3-VL-30B-A3B | 8.44 | Not recorded | 68fa77611e209131cea72d93 |
| Qwen3-VL-8B | 7.99 | Not recorded | 68fa77611e209131cea72d93 |
| Qwen2.5-VL-7B | 7.84 | Not recorded | 68fa77611e209131cea72d93 |
| Claude4-Sonnet | 7.84 | Not recorded | 68fa77611e209131cea72d93 |
| GPT-4o | 7.67 | Not recorded | 68fa77611e209131cea72d93 |
| Omni-Emotion | 7.53 | Not recorded | 68fa77611e209131cea72d93 |
| HumanOmni | 7.51 | Not recorded | 68fa77611e209131cea72d93 |
| PLLaVA | 7.47 | Not recorded | 68fa77611e209131cea72d93 |
| FaceTrack-MM | 7.47 | Not recorded | 68fa77611e209131cea72d93 |
| Emotion-LLaMA | 7.42 | Not recorded | 68fa77611e209131cea72d93 |
| VideoLLaMA2 | 7.41 | Not recorded | 68fa77611e209131cea72d93 |
| ShareGPT4Video | 7.33 | Not recorded | 68fa77611e209131cea72d93 |
| LLaVA-Next-Video | 7.14 | Not recorded | 68fa77611e209131cea72d93 |
| Qwen2.5-VL-3B | 7.01 | Not recorded | 68fa77611e209131cea72d93 |
| LLaMA-VID | 6.98 | Not recorded | 68fa77611e209131cea72d93 |
| ST-LLM | 6.79 | Not recorded | 68fa77611e209131cea72d93 |
| Chat-UniVI | 6.76 | Not recorded | 68fa77611e209131cea72d93 |
| LLaVA-OneVision | 6.72 | Not recorded | 68fa77611e209131cea72d93 |
| Face-MLLM | 6.62 | Not recorded | 68fa77611e209131cea72d93 |
| VideoChat2 | 6.47 | Not recorded | 68fa77611e209131cea72d93 |
| Tarsier | 6.42 | Not recorded | 68fa77611e209131cea72d93 |
| VideoLLaMA | 6.12 | Not recorded | 68fa77611e209131cea72d93 |
| VideoChat | 5.92 | Not recorded | 68fa77611e209131cea72d93 |

### FaVChat-Qwen3

VideoChatGPT Score (Overall): 9.01. Result ID: 69d35d2b47f34ce924bab739.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

Recorded evaluation configuration: {"LLM Size":"8B"}. This record does not assert independent reproduction.

### FaVChat-Qwen2.5

VideoChatGPT Score (Overall): 8.89. Result ID: 69d35d2b47f34ce924bab738.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### Qwen3-VL-8B-Face

VideoChatGPT Score (Overall): 8.87. Result ID: 69d35d2b47f34ce924bab734.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"LLM Size":"8B","Fine-tuning Dataset":"FaVChat-170K"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B-Face

VideoChatGPT Score (Overall): 8.64. Result ID: 69d35d2b47f34ce924bab733.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Fine-tuning Dataset":"FaVChat-170K"}. This record does not assert independent reproduction.

### Qwen2.5-VL-72B

VideoChatGPT Score (Overall): 8.47. Result ID: 69d35d2b47f34ce924bab72b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"LLM Size":"72B"}. This record does not assert independent reproduction.

### Qwen3-VL-30B-A3B

VideoChatGPT Score (Overall): 8.44. Result ID: 69d35d2b47f34ce924bab72e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"LLM Size":"30B"}. This record does not assert independent reproduction.

### Qwen3-VL-8B

VideoChatGPT Score (Overall): 7.99. Result ID: 69d35d2b47f34ce924bab72d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"LLM Size":"8B"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

VideoChatGPT Score (Overall): 7.84. Result ID: 69d35d2b47f34ce924bab72a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### Claude4-Sonnet

VideoChatGPT Score (Overall): 7.84. Result ID: 69d35d2b47f34ce924bab72f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

Recorded evaluation configuration: {"LLM Size":"-"}. This record does not assert independent reproduction.

### GPT-4o

VideoChatGPT Score (Overall): 7.67. Result ID: 69d35d2b47f34ce924bab730.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"LLM Size":"-"}. This record does not assert independent reproduction.

### Omni-Emotion

VideoChatGPT Score (Overall): 7.53. Result ID: 69d35d2b47f34ce924bab737.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76951e209131cea6ddd2.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Training Modalities":"visual and speech"}. This record does not assert independent reproduction.

### HumanOmni

VideoChatGPT Score (Overall): 7.51. Result ID: 69d35d2b47f34ce924bab736.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecef.md>)

Recorded evaluation configuration: {"LLM Size":"7B","Training Modalities":"visual and speech"}. This record does not assert independent reproduction.

### PLLaVA

VideoChatGPT Score (Overall): 7.47. Result ID: 69d35d2b47f34ce924bab726.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a3ea.md>)

[Implementation](<https://pllava.github.io/>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### FaceTrack-MM

VideoChatGPT Score (Overall): 7.47. Result ID: 69d35d2b47f34ce924bab732.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76971e209131cea6dfd5.md>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### Emotion-LLaMA

VideoChatGPT Score (Overall): 7.42. Result ID: 69d35d2b47f34ce924bab735.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

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

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

Recorded evaluation configuration: {"LLM Size":"7B","Training Modalities":"visual and speech"}. This record does not assert independent reproduction.

### VideoLLaMA2

VideoChatGPT Score (Overall): 7.41. Result ID: 69d35d2b47f34ce924bab725.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75761e209131cea681dd.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/VideoLLaMA2>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### ShareGPT4Video

VideoChatGPT Score (Overall): 7.33. Result ID: 69d35d2b47f34ce924bab723.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738e1e209131cea5d310.md>)

[Implementation](<https://sharegpt4video.github.io/>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### LLaVA-Next-Video

VideoChatGPT Score (Overall): 7.14. Result ID: 69d35d2b47f34ce924bab722.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### Qwen2.5-VL-3B

VideoChatGPT Score (Overall): 7.01. Result ID: 69d35d2b47f34ce924bab72c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

Recorded evaluation configuration: {"LLM Size":"2B"}. This record does not assert independent reproduction.

### LLaMA-VID

VideoChatGPT Score (Overall): 6.98. Result ID: 69d35d2b47f34ce924bab724.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

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

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

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### ST-LLM

VideoChatGPT Score (Overall): 6.79. Result ID: 69d35d2b47f34ce924bab727.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bd1e209131cea584a2.md>)

[Implementation](<https://github.com/TencentARC/ST-LLM>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### Chat-UniVI

VideoChatGPT Score (Overall): 6.76. Result ID: 69d35d2b47f34ce924bab721.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

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

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

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### LLaVA-OneVision

VideoChatGPT Score (Overall): 6.72. Result ID: 69d35d2b47f34ce924bab729.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e58.md>)

[Implementation](<https://llava-vl.github.io/blog/llava-onevision>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### Face-MLLM

VideoChatGPT Score (Overall): 6.62. Result ID: 69d35d2b47f34ce924bab731.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a05.md>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### VideoChat2

VideoChatGPT Score (Overall): 6.47. Result ID: 69d35d2b47f34ce924bab720.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

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

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### Tarsier

VideoChatGPT Score (Overall): 6.42. Result ID: 69d35d2b47f34ce924bab728.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e41e209131cea64782.md>)

[Implementation](<https://github.com/bytedance/tarsier>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### VideoLLaMA

VideoChatGPT Score (Overall): 6.12. Result ID: 69d35d2b47f34ce924bab71e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f11e209131cea4e393.md>)

[Implementation](<https://github.com/DAMO-NLP-SG/Video-LLaMA>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

### VideoChat

VideoChatGPT Score (Overall): 5.92. Result ID: 69d35d2b47f34ce924bab71f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77611e209131cea72d93.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52cc7.md>)

Recorded evaluation configuration: {"LLM Size":"7B"}. This record does not assert independent reproduction.

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