# Text-rich Visual Comprehension on SEED-Bench 2-Plus

Source: [Text-rich Visual Comprehension on SEED-Bench 2-Plus](<https://www.sota2.com/research/sota/text-rich-visual-comprehension-on-seed-bench-2-plus>)

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

Data updated: 2026-06-01T07:34:17.884Z

Evaluation of Text-rich Visual Comprehension capabilities using the SEED-Bench 2-Plus dataset, measured by Accuracy.

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 | Text-rich Visual Comprehension |
| Dataset (including any stated split) | SEED-Bench 2-Plus |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/text-rich-visual-comprehension-on-seed-bench-2-plus.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ReGuLaR-7B | 70.22 | Not recorded | 6a1d120bdbd7150506f83f6d |
| Laser | 70.05 | Not recorded | 6a1d120bdbd7150506f83f6d |
| Deepeyes | 69.08 | Not recorded | 6a1d120bdbd7150506f83f6d |
| Vision-R1 | 68.95 | Not recorded | 6a1d120bdbd7150506f83f6d |
| Monet | 65.88 | Not recorded | 6a1d120bdbd7150506f83f6d |
| Qwen2.5-VL-7B | 65.31 | Not recorded | 6a1d120bdbd7150506f83f6d |
| LLaVA-OneVision | 61.22 | Not recorded | 6a1d120bdbd7150506f83f6d |
| PAPO | 54.11 | Not recorded | 6a1d120bdbd7150506f83f6d |
| LVR | 47.39 | Not recorded | 6a1d120bdbd7150506f83f6d |

### ReGuLaR-7B

Accuracy: 70.22. Result ID: 6a1d35cbfbc373592c16079f.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

Recorded evaluation configuration: {"Model Category":"Latent reasoning LVLMs"}. This record does not assert independent reproduction.

### Laser

Accuracy: 70.05. Result ID: 6a1d35cbfbc373592c16079e.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6965d1706343fa78c8323443.md>)

Recorded evaluation configuration: {"Model Category":"Latent reasoning LVLMs"}. This record does not assert independent reproduction.

### Deepeyes

Accuracy: 69.08. Result ID: 6a1d35cbfbc373592c160799.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c71e209131cea7a75e.md>)

Recorded evaluation configuration: {"Model Category":"RL-based reasoning LVLMs"}. This record does not assert independent reproduction.

### Vision-R1

Accuracy: 68.95. Result ID: 6a1d35cbfbc373592c16079b.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77591e209131cea72979.md>)

Recorded evaluation configuration: {"Model Category":"RL-based reasoning LVLMs"}. This record does not assert independent reproduction.

### Monet

Accuracy: 65.88. Result ID: 6a1d35cbfbc373592c16079d.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db45d6b0dd3342930e7a.md>)

[Implementation](<https://github.com/NOVAglow646/Monet>)

Recorded evaluation configuration: {"Model Category":"Latent reasoning LVLMs"}. This record does not assert independent reproduction.

### Qwen2.5-VL-7B

Accuracy: 65.31. Result ID: 6a1d35cbfbc373592c160798.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

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

Recorded evaluation configuration: {"Model Category":"General-purpose LVLMs"}. This record does not assert independent reproduction.

### LLaVA-OneVision

Accuracy: 61.22. Result ID: 6a1d35cbfbc373592c160797.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.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 Category":"General-purpose LVLMs"}. This record does not assert independent reproduction.

### PAPO

Accuracy: 54.11. Result ID: 6a1d35cbfbc373592c16079a.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a761e209131cea8363f.md>)

Recorded evaluation configuration: {"Model Category":"RL-based reasoning LVLMs"}. This record does not assert independent reproduction.

### LVR

Accuracy: 47.39. Result ID: 6a1d35cbfbc373592c16079c.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d120bdbd7150506f83f6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be71e209131cea8b35b.md>)

Recorded evaluation configuration: {"Model Category":"Latent reasoning LVLMs"}. This record does not assert independent reproduction.

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