# Comprehensive Evaluation on VizWiz (val)

Source: [Comprehensive Evaluation on VizWiz (val)](<https://www.sota2.com/research/sota/comprehensive-evaluation-on-vizwiz-val>)

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

Data updated: 2026-02-26T06:03:47.806Z

Evaluation of general model performance using a comprehensive set of metrics on the validation split of the VizWiz dataset.

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 | Comprehensive Evaluation |
| Dataset (including any stated split) | VizWiz (val) |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Score](<https://www.sota2.com/research/sota/comprehensive-evaluation-on-vizwiz-val.md?metric=Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| MetaGPT | 69.16 | Not recorded | 68fa77ae1e209131cea74acd |
| AdaMMS | 68.4 | Not recorded | 68fa77ae1e209131cea74acd |
| Qwen2-VL (base) | 68.32 | Not recorded | 68fa77ae1e209131cea74acd |
| Ties-Merging | 66.34 | Not recorded | 68fa77ae1e209131cea74acd |
| Task Arithmetic | 62.76 | Not recorded | 68fa77ae1e209131cea74acd |
| LLaVA-OneVision | 60.97 | Not recorded | 68fa77ae1e209131cea74acd |
| DARE-Ties | 58.05 | Not recorded | 68fa77ae1e209131cea74acd |
| LLaVA-v1.5-7B | 54.29 | Not recorded | 68fa77ae1e209131cea74acd |
| DARE-Linear | 50.18 | Not recorded | 68fa77ae1e209131cea74acd |
| AdaMMS | 37.27 | Not recorded | 68fa77ae1e209131cea74acd |
| CogVLM-chat-7B | 37.09 | Not recorded | 68fa77ae1e209131cea74acd |
| MetaGPT | 36.97 | Not recorded | 68fa77ae1e209131cea74acd |
| DARE-Linear | 36.12 | Not recorded | 68fa77ae1e209131cea74acd |
| Task Arithmetic | 35.7 | Not recorded | 68fa77ae1e209131cea74acd |
| DARE-Ties | 31.43 | Not recorded | 68fa77ae1e209131cea74acd |
| Ties-Merging | 24.36 | Not recorded | 68fa77ae1e209131cea74acd |

### MetaGPT

Score: 69.16. Result ID: 69955cc63badfaffe64e7737.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d51e209131cea5e673.md>)

Recorded evaluation configuration: {"merging\_target":"Qwen2-VL-7B","merging\_source":"LLaVA-OneVision-7B"}. This record does not assert independent reproduction.

### AdaMMS

Score: 68.4. Result ID: 69955cc63badfaffe64e7738.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Implementation](<https://github.com/THUNLP-MT/AdaMMS>)

Recorded evaluation configuration: {"merging\_target":"Qwen2-VL-7B","merging\_source":"LLaVA-OneVision-7B"}. This record does not assert independent reproduction.

### Qwen2-VL (base)

Score: 68.32. Result ID: 69955cc63badfaffe64e7731.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75151e209131cea65976.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-VL>)

Recorded evaluation configuration: {"model\_status":"Original Model"}. This record does not assert independent reproduction.

### Ties-Merging

Score: 66.34. Result ID: 69955cc63badfaffe64e7734.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecd8.md>)

Recorded evaluation configuration: {"merging\_target":"Qwen2-VL-7B","merging\_source":"LLaVA-OneVision-7B"}. This record does not assert independent reproduction.

### Task Arithmetic

Score: 62.76. Result ID: 69955cc63badfaffe64e7733.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef01e209131cea43012.md>)

Recorded evaluation configuration: {"merging\_target":"Qwen2-VL-7B","merging\_source":"LLaVA-OneVision-7B"}. This record does not assert independent reproduction.

### LLaVA-OneVision

Score: 60.97. Result ID: 69955cc63badfaffe64e7732.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

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

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

Recorded evaluation configuration: {"model\_status":"Original Model"}. This record does not assert independent reproduction.

### DARE-Ties

Score: 58.05. Result ID: 69955cc63badfaffe64e7736.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73921e209131cea5d4aa.md>)

Recorded evaluation configuration: {"merging\_target":"Qwen2-VL-7B","merging\_source":"LLaVA-OneVision-7B"}. This record does not assert independent reproduction.

### LLaVA-v1.5-7B

Score: 54.29. Result ID: 69955cc63badfaffe64e76ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732e1e209131cea5af59.md>)

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

Recorded evaluation configuration: {"Status":"Source Model"}. This record does not assert independent reproduction.

### DARE-Linear

Score: 50.18. Result ID: 69955cc63badfaffe64e7735.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73921e209131cea5d4aa.md>)

Recorded evaluation configuration: {"merging\_target":"Qwen2-VL-7B","merging\_source":"LLaVA-OneVision-7B"}. This record does not assert independent reproduction.

### AdaMMS

Score: 37.27. Result ID: 69955cc63badfaffe64e76c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Implementation](<https://github.com/THUNLP-MT/AdaMMS>)

Recorded evaluation configuration: {"Merging Protocol":"AdaMMS"}. This record does not assert independent reproduction.

### CogVLM-chat-7B

Score: 37.09. Result ID: 69955cc63badfaffe64e76b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa721c1e209131cea548b9.md>)

[Implementation](<https://github.com/THUDM/CogVLM>)

Recorded evaluation configuration: {"Status":"Base Model"}. This record does not assert independent reproduction.

### MetaGPT

Score: 36.97. Result ID: 69955cc63badfaffe64e76bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73d51e209131cea5e673.md>)

Recorded evaluation configuration: {"Merging Protocol":"MetaGPT"}. This record does not assert independent reproduction.

### DARE-Linear

Score: 36.12. Result ID: 69955cc63badfaffe64e76bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73921e209131cea5d4aa.md>)

Recorded evaluation configuration: {"Merging Protocol":"DARE-Linear"}. This record does not assert independent reproduction.

### Task Arithmetic

Score: 35.7. Result ID: 69955cc63badfaffe64e76bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef01e209131cea43012.md>)

Recorded evaluation configuration: {"Merging Protocol":"Task Arithmetic"}. This record does not assert independent reproduction.

### DARE-Ties

Score: 31.43. Result ID: 69955cc63badfaffe64e76be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73921e209131cea5d4aa.md>)

Recorded evaluation configuration: {"Merging Protocol":"DARE-Ties"}. This record does not assert independent reproduction.

### Ties-Merging

Score: 24.36. Result ID: 69955cc63badfaffe64e76bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77ae1e209131cea74acd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecd8.md>)

Recorded evaluation configuration: {"Merging Protocol":"Ties-Merging"}. This record does not assert independent reproduction.

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