# STEM Reasoning on MMMU (val)

Source: [STEM Reasoning on MMMU (val)](<https://www.sota2.com/research/sota/stem-reasoning-on-mmmu-val>)

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

Data updated: 2026-04-29T07:11:39.840Z

Evaluation of model performance on the STEM Reasoning task using the validation split of the MMMU 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 | STEM Reasoning |
| Dataset (including any stated split) | MMMU (val) |
| Metric | STEM Reasoning Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [STEM Reasoning Score](<https://www.sota2.com/research/sota/stem-reasoning-on-mmmu-val.md?metric=STEM%20Reasoning%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | STEM Reasoning Score | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3.5-Omni | 76.9 | Not recorded | 69f1907355a3c32af89fb98b |
| Qwen3-Omni | 75.6 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron 3 Nano Omni | 70.8 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron Nano V2 VL | 67.8 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron Nano V2 VL | 55.3 | Not recorded | 69f1907355a3c32af89fb98b |
| Nemotron 3 Nano Omni | 55.2 | Not recorded | 69f1907355a3c32af89fb98b |

### Qwen3.5-Omni

STEM Reasoning Score: 76.9. Result ID: 69f1ae5847f34ce924d7aea7.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

Recorded evaluation configuration: {"Open-Source":"false","Size":"Flash"}. This record does not assert independent reproduction.

### Qwen3-Omni

STEM Reasoning Score: 75.6. Result ID: 69f1ae5847f34ce924d7aea6.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b881e209131cea88f3d.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"30B-A3B"}. This record does not assert independent reproduction.

### Nemotron 3 Nano Omni

STEM Reasoning Score: 70.8. Result ID: 69f1ae5847f34ce924d7aea3.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"30B-A3B","Reasoning":"on"}. This record does not assert independent reproduction.

### Nemotron Nano V2 VL

STEM Reasoning Score: 67.8. Result ID: 69f1ae5847f34ce924d7aea5.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690d7d0b2828b7cc6937ce26.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"12B","Reasoning":"on"}. This record does not assert independent reproduction.

### Nemotron Nano V2 VL

STEM Reasoning Score: 55.3. Result ID: 69f1ae5847f34ce924d7aea4.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690d7d0b2828b7cc6937ce26.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"12B","Reasoning":"off"}. This record does not assert independent reproduction.

### Nemotron 3 Nano Omni

STEM Reasoning Score: 55.2. Result ID: 69f1ae5847f34ce924d7aea2.

[Reporting paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1907355a3c32af89fb98b.md>)

Recorded evaluation configuration: {"Open-Source":"true","Size":"30B-A3B","Reasoning":"off"}. This record does not assert independent reproduction.

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