# Large Multi-modal Model Evaluation on LLaVA-Bench In-the-Wild v1

Source: [Large Multi-modal Model Evaluation on LLaVA-Bench In-the-Wild v1](<https://www.sota2.com/research/sota/large-multi-modal-model-evaluation-on-llava-bench-in-the-wild-v1>)

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

Data updated: 2026-02-26T05:39:51.052Z

Evaluation of large multimodal model performance using the LLaVA-Bench In-the-Wild v1 dataset, focusing on conversational ability, detail retention, and reasoning skills.

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 | Large Multi-modal Model Evaluation |
| Dataset (including any stated split) | LLaVA-Bench In-the-Wild v1 |
| Metric | Conversational Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Conversational Score](<https://www.sota2.com/research/sota/large-multi-modal-model-evaluation-on-llava-bench-in-the-wild-v1.md?metric=Conversational%20Score>): Higher is better; unit: PERCENT.

- [Detail Retention Score](<https://www.sota2.com/research/sota/large-multi-modal-model-evaluation-on-llava-bench-in-the-wild-v1.md?metric=Detail%20Retention%20Score>): Higher is better; unit: PERCENT.

- [Reasoning Score](<https://www.sota2.com/research/sota/large-multi-modal-model-evaluation-on-llava-bench-in-the-wild-v1.md?metric=Reasoning%20Score>): Higher is better; unit: PERCENT.

- [Overall Score](<https://www.sota2.com/research/sota/large-multi-modal-model-evaluation-on-llava-bench-in-the-wild-v1.md?metric=Overall%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Conversational Score | Result date | Report paper |
| --- | --- | --- | --- |
| LLaVA-Plus | 65.5 | Not recorded | 68fa71201e209131cea4f4e0 |
| LLaVA-Plus | 45.2 | Not recorded | 68fa71201e209131cea4f4e0 |
| LLaVA | 42.6 | Not recorded | 68fa71201e209131cea4f4e0 |
| LLaVA | 40.7 | Not recorded | 68fa71201e209131cea4f4e0 |
| LLaVA-Plus | 38.8 | Not recorded | 68fa71201e209131cea4f4e0 |
| GPT4Tools | 31.1 | Not recorded | 68fa71201e209131cea4f4e0 |

### LLaVA-Plus

Conversational Score: 65.5. Result ID: 6991b4c33a6c3148490a0d87.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

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

Recorded evaluation configuration: {"tool\_usage":"All Tools"}. This record does not assert independent reproduction.

### LLaVA-Plus

Conversational Score: 45.2. Result ID: 6991b4c33a6c3148490a0d88.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

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

Recorded evaluation configuration: {"tool\_usage":"Fly"}. This record does not assert independent reproduction.

### LLaVA

Conversational Score: 42.6. Result ID: 6991b4c33a6c3148490a0d85.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

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

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

### LLaVA

Conversational Score: 40.7. Result ID: 6991b4c33a6c3148490a0d86.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717d1e209131cea51970.md>)

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

Recorded evaluation configuration: {"evaluation\_protocol":"Tools in Test"}. This record does not assert independent reproduction.

### LLaVA-Plus

Conversational Score: 38.8. Result ID: 6991b4c33a6c3148490a0d89.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

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

Recorded evaluation configuration: {"tool\_usage":"Fly","reasoning\_thoughts":false}. This record does not assert independent reproduction.

### GPT4Tools

Conversational Score: 31.1. Result ID: 6991b4c33a6c3148490a0d8a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71201e209131cea4f4e0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f941e209131cea46699.md>)

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.
