# Embodied Question Answering on OpenEQA (test)

Source: [Embodied Question Answering on OpenEQA (test)](<https://www.sota2.com/research/sota/embodied-question-answering-on-openeqa-test>)

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

Data updated: 2026-03-31T09:03:47.857Z

Evaluation of model performance on the test split of the OpenEQA dataset for Embodied Question Answering, typically measured using metrics like GPT-4 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 | Embodied Question Answering |
| Dataset (including any stated split) | OpenEQA (test) |
| Metric | GPT-4 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 18 of 18 |
| 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

- [GPT-4 Score](<https://www.sota2.com/research/sota/embodied-question-answering-on-openeqa-test.md?metric=GPT-4%20Score>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/embodied-question-answering-on-openeqa-test.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | GPT-4 Score | Result date | Report paper |
| --- | --- | --- | --- |
| Human | 86.8 | Not recorded | 68fa76bb1e209131cea6ecbe |
| Human | 86.8 | Not recorded | 68fa76bb1e209131cea6ecbe |
| Tarsier2 | 58.7 | Not recorded | 68fa76bb1e209131cea6ecbe |
| Tarsier2 | 58.7 | Not recorded | 68fa76bb1e209131cea6ecbe |
| GPT-4V | 55.3 | Not recorded | 68fa76bb1e209131cea6ecbe |
| GPT-4V | 55.3 | Not recorded | 68fa76bb1e209131cea6ecbe |
| MLCD | 48.8 | Not recorded | 68fa76bb1e209131cea6ecbe |
| MLCD | 48.8 | Not recorded | 68fa76bb1e209131cea6ecbe |
| Gemini-1.5-Pro | 44.9 | Not recorded | 68fa76bb1e209131cea6ecbe |
| Gemini-1.5-Pro | 44.9 | Not recorded | 68fa76bb1e209131cea6ecbe |

### Human

GPT-4 Score: 86.8. Result ID: 699460523a6c3148491cd98a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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

### Human

GPT-4 Score: 86.8. Result ID: 699460523a6c3148491cd9b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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

### Tarsier2

GPT-4 Score: 58.7. Result ID: 699460523a6c3148491cd98e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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

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

### Tarsier2

GPT-4 Score: 58.7. Result ID: 699460523a6c3148491cd9b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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

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

### GPT-4V

GPT-4 Score: 55.3. Result ID: 699460523a6c3148491cd98b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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

### GPT-4V

GPT-4 Score: 55.3. Result ID: 699460523a6c3148491cd9b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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

### MLCD

GPT-4 Score: 48.8. Result ID: 699460523a6c3148491cd98d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa758d1e209131cea688d2.md>)

[Implementation](<https://github.com/deepglint/unicom>)

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

### MLCD

GPT-4 Score: 48.8. Result ID: 699460523a6c3148491cd9b7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa758d1e209131cea688d2.md>)

[Implementation](<https://github.com/deepglint/unicom>)

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

### Gemini-1.5-Pro

GPT-4 Score: 44.9. Result ID: 699460523a6c3148491cd98c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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

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

### Gemini-1.5-Pro

GPT-4 Score: 44.9. Result ID: 699460523a6c3148491cd9b6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76bb1e209131cea6ecbe.md>)

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