# Expert/Academic Reasoning on MMMU (Pass@5, Avg@5)

Source: [Expert/Academic Reasoning on MMMU (Pass@5, Avg@5)](<https://www.sota2.com/research/sota/expert-academic-reasoning-on-mmmu-pass-at-5-avg-at-5>)

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

Data updated: 2026-06-18T08:38:20.455Z

Evaluation of model performance on the MMMU dataset focusing on expert and academic reasoning capabilities, measured using Pass@5 and Avg@5 metrics.

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 | Expert/Academic Reasoning |
| Dataset (including any stated split) | MMMU |
| Metric | Pass@5 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Pass@5 Score](<https://www.sota2.com/research/sota/expert-academic-reasoning-on-mmmu-pass-at-5-avg-at-5.md?metric=Pass%405%20Score>): Higher is better; unit: PERCENT.

- [Avg@5 Score](<https://www.sota2.com/research/sota/expert-academic-reasoning-on-mmmu-pass-at-5-avg-at-5.md?metric=Avg%405%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@5 Score | Result date | Report paper |
| --- | --- | --- | --- |
| ViGOS | 80.11 | Not recorded | 6a337b96206542251d7c50d7 |
| OPSD | 77.99 | Not recorded | 6a337b96206542251d7c50d7 |
| Baseline | 77.77 | Not recorded | 6a337b96206542251d7c50d7 |
| OPSD | 76.42 | Not recorded | 6a337b96206542251d7c50d7 |
| ViGOS | 76.42 | Not recorded | 6a337b96206542251d7c50d7 |
| Baseline | 71.51 | Not recorded | 6a337b96206542251d7c50d7 |
| Visionary-R1-3B | 70.28 | Not recorded | 6a337b96206542251d7c50d7 |
| Vision-R1-7B | 64.69 | Not recorded | 6a337b96206542251d7c50d7 |

### ViGOS

Pass@5 Score: 80.11. Result ID: 6a33ae6efbc373592c310715.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

[Implementation](<https://github.com/OedoSoldier/ViGOS>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL 7B"}. This record does not assert independent reproduction.

### OPSD

Pass@5 Score: 77.99. Result ID: 6a33ae6efbc373592c310714.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6978471ca2b28e761d87ca01.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL 7B"}. This record does not assert independent reproduction.

### Baseline

Pass@5 Score: 77.77. Result ID: 6a33ae6efbc373592c310713.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

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

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL 7B"}. This record does not assert independent reproduction.

### OPSD

Pass@5 Score: 76.42. Result ID: 6a33ae6efbc373592c310711.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6978471ca2b28e761d87ca01.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL 3B"}. This record does not assert independent reproduction.

### ViGOS

Pass@5 Score: 76.42. Result ID: 6a33ae6efbc373592c310712.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

[Implementation](<https://github.com/OedoSoldier/ViGOS>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL 3B"}. This record does not assert independent reproduction.

### Baseline

Pass@5 Score: 71.51. Result ID: 6a33ae6efbc373592c310710.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

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

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL 3B"}. This record does not assert independent reproduction.

### Visionary-R1-3B

Pass@5 Score: 70.28. Result ID: 6a33ae6efbc373592c31070e.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c4a1e209131cea8d6ab.md>)

Recorded evaluation configuration: {"Method Category":"RL Method"}. This record does not assert independent reproduction.

### Vision-R1-7B

Pass@5 Score: 64.69. Result ID: 6a33ae6efbc373592c31070f.

[Reporting paper](<https://www.sota2.com/research/paper/6a337b96206542251d7c50d7.md>)

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

Recorded evaluation configuration: {"Method Category":"RL Method"}. This record does not assert independent reproduction.

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