# Real-world Multimodal Interaction on RealWorldQA

Source: [Real-world Multimodal Interaction on RealWorldQA](<https://www.sota2.com/research/sota/real-world-multimodal-interaction-on-realworldqa>)

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

Data updated: 2026-02-26T06:01:09.435Z

Evaluation of model performance on the RealWorldQA dataset for real-world multimodal interaction tasks, measured by the RealWorldQA 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 | Real-world Multimodal Interaction |
| Dataset (including any stated split) | RealWorldQA |
| Metric | RealWorldQA Score |
| 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

- [RealWorldQA Score](<https://www.sota2.com/research/sota/real-world-multimodal-interaction-on-realworldqa.md?metric=RealWorldQA%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | RealWorldQA Score | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 76.5 | Not recorded | 69535c8653fdd5c36173d9b8 |
| MAmmoTH-VL | 71.3 | Not recorded | 69535c8653fdd5c36173d9b8 |
| InternVL3 | 70.8 | Not recorded | 69535c8653fdd5c36173d9b8 |
| Molmo-8B-D | 70.7 | Not recorded | 69535c8653fdd5c36173d9b8 |
| Gemini-1.5 Pro | 70.4 | Not recorded | 69535c8653fdd5c36173d9b8 |
| MAmmoTH-VL | 69.9 | Not recorded | 69535c8653fdd5c36173d9b8 |
| Qwen2.5-VL | 68.5 | Not recorded | 69535c8653fdd5c36173d9b8 |
| DeepSeek-VL2 | 68.4 | Not recorded | 69535c8653fdd5c36173d9b8 |
| Dream-VL | 68.4 | Not recorded | 69535c8653fdd5c36173d9b8 |
| LLaVA-OV | 66.3 | Not recorded | 69535c8653fdd5c36173d9b8 |
| Dream-VL | 66.3 | Not recorded | 69535c8653fdd5c36173d9b8 |
| LLaVA-OV | 65.5 | Not recorded | 69535c8653fdd5c36173d9b8 |
| Cambrian-1 | 64.2 | Not recorded | 69535c8653fdd5c36173d9b8 |
| LLaDA-V | 63.2 | Not recorded | 69535c8653fdd5c36173d9b8 |
| Claude 3.5 Sonnet | 60.1 | Not recorded | 69535c8653fdd5c36173d9b8 |

### GPT-4o

RealWorldQA Score: 76.5. Result ID: 699806af5698665ec46037e1.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

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

Recorded evaluation configuration: {"LLM Backbone":null,"Open Data":false,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### MAmmoTH-VL

RealWorldQA Score: 71.3. Result ID: 699806af5698665ec46037eb.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79201e209131cea7c422.md>)

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

Recorded evaluation configuration: {"LLM Backbone":"Qwen2.5-7B","Open Data":true,"Super-Image (SI)":true}. This record does not assert independent reproduction.

### InternVL3

RealWorldQA Score: 70.8. Result ID: 699806af5698665ec46037e6.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78241e209131cea76fa5.md>)

Recorded evaluation configuration: {"LLM Backbone":"Qwen2.5-7B","Open Data":false,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### Molmo-8B-D

RealWorldQA Score: 70.7. Result ID: 699806af5698665ec46037e8.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76101e209131cea6b37c.md>)

[Implementation](<https://molmo.allenai.org/>)

Recorded evaluation configuration: {"LLM Backbone":"Qwen2 7B","Open Data":true,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### Gemini-1.5 Pro

RealWorldQA Score: 70.4. Result ID: 699806af5698665ec46037e2.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76361e209131cea6be11.md>)

Recorded evaluation configuration: {"LLM Backbone":null,"Open Data":false,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### MAmmoTH-VL

RealWorldQA Score: 69.9. Result ID: 699806af5698665ec46037ec.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79201e209131cea7c422.md>)

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

Recorded evaluation configuration: {"LLM Backbone":"Qwen2.5-7B","Open Data":true,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### Qwen2.5-VL

RealWorldQA Score: 68.5. Result ID: 699806af5698665ec46037e5.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

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

Recorded evaluation configuration: {"LLM Backbone":"Qwen2.5-7B","Open Data":false,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### DeepSeek-VL2

RealWorldQA Score: 68.4. Result ID: 699806af5698665ec46037e4.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa763a1e209131cea6bfb0.md>)

Recorded evaluation configuration: {"LLM Backbone":"DeepSeek-MoE 27B","Open Data":false,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### Dream-VL

RealWorldQA Score: 68.4. Result ID: 699806af5698665ec46037ee.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Implementation](<https://github.com/DreamLM/Dream-VLX>)

Recorded evaluation configuration: {"LLM Backbone":"Dream 7B","Open Data":true,"Super-Image (SI)":true}. This record does not assert independent reproduction.

### LLaVA-OV

RealWorldQA Score: 66.3. Result ID: 699806af5698665ec46037ea.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.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 Backbone":"Qwen2-7B","Open Data":true,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### Dream-VL

RealWorldQA Score: 66.3. Result ID: 699806af5698665ec46037ef.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Implementation](<https://github.com/DreamLM/Dream-VLX>)

Recorded evaluation configuration: {"LLM Backbone":"Dream 7B","Open Data":true,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### LLaVA-OV

RealWorldQA Score: 65.5. Result ID: 699806af5698665ec46037e9.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.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 Backbone":"Qwen2-7B","Open Data":true,"Super-Image (SI)":true}. This record does not assert independent reproduction.

### Cambrian-1

RealWorldQA Score: 64.2. Result ID: 699806af5698665ec46037e7.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75fa1e209131cea6ac2e.md>)

Recorded evaluation configuration: {"LLM Backbone":"LLaMA3-8B","Open Data":true,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### LLaDA-V

RealWorldQA Score: 63.2. Result ID: 699806af5698665ec46037ed.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79101e209131cea7bebe.md>)

Recorded evaluation configuration: {"LLM Backbone":"LLaDA 8B","Open Data":true,"Super-Image (SI)":false}. This record does not assert independent reproduction.

### Claude 3.5 Sonnet

RealWorldQA Score: 60.1. Result ID: 699806af5698665ec46037e3.

[Reporting paper](<https://www.sota2.com/research/paper/69535c8653fdd5c36173d9b8.md>)

Recorded evaluation configuration: {"LLM Backbone":null,"Open Data":false,"Super-Image (SI)":false}. This record does not assert independent reproduction.

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