# Multilingual Robustness Evaluation on MULTYPO (test)

Source: [Multilingual Robustness Evaluation on MULTYPO (test)](<https://www.sota2.com/research/sota/multilingual-robustness-evaluation-on-multypo-test>)

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

Data updated: 2026-04-15T09:13:17.845Z

Evaluation of model robustness across multiple languages using the MULTYPO test set, focusing on performance degradation 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 | Multilingual Robustness Evaluation |
| Dataset (including any stated split) | MULTYPO (test) |
| Metric | Average Score |
| Unit | SCALAR |
| 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

- [Average Score](<https://www.sota2.com/research/sota/multilingual-robustness-evaluation-on-multypo-test.md?metric=Average%20Score>): Higher is better; unit: SCALAR.

- [Relative Performance Drop](<https://www.sota2.com/research/sota/multilingual-robustness-evaluation-on-multypo-test.md?metric=Relative%20Performance%20Drop>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Average Score | Result date | Report paper |
| --- | --- | --- | --- |
| Gemma | 59.11 | Not recorded | 68fa7c111e209131cea8c426 |
| Gemma | 48.5 | Not recorded | 68fa7c111e209131cea8c426 |
| Qwen | 47.19 | Not recorded | 68fa7c111e209131cea8c426 |
| Qwen | 44.5 | Not recorded | 68fa7c111e209131cea8c426 |
| OLMo | 36.82 | Not recorded | 68fa7c111e209131cea8c426 |
| OLMo | 29.16 | Not recorded | 68fa7c111e209131cea8c426 |
| Qwen | 27.86 | Not recorded | 68fa7c111e209131cea8c426 |
| Gemma | 21.46 | Not recorded | 68fa7c111e209131cea8c426 |
| OLMo | 16.3 | Not recorded | 68fa7c111e209131cea8c426 |

### Gemma

Average Score: 59.11. Result ID: 69df569d47f34ce924c85024.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Model Size":"Large","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### Gemma

Average Score: 48.5. Result ID: 69df569d47f34ce924c85023.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Model Size":"Medium","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### Qwen

Average Score: 47.19. Result ID: 69df569d47f34ce924c8502a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Size":"Large","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### Qwen

Average Score: 44.5. Result ID: 69df569d47f34ce924c85029.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Size":"Medium","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### OLMo

Average Score: 36.82. Result ID: 69df569d47f34ce924c85027.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf21e209131cea8b84e.md>)

Recorded evaluation configuration: {"Model Size":"Large","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### OLMo

Average Score: 29.16. Result ID: 69df569d47f34ce924c85026.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf21e209131cea8b84e.md>)

Recorded evaluation configuration: {"Model Size":"Medium","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### Qwen

Average Score: 27.86. Result ID: 69df569d47f34ce924c85028.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Size":"Small","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### Gemma

Average Score: 21.46. Result ID: 69df569d47f34ce924c85022.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Model Size":"Small","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

### OLMo

Average Score: 16.3. Result ID: 69df569d47f34ce924c85025.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c111e209131cea8c426.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf21e209131cea8b84e.md>)

Recorded evaluation configuration: {"Model Size":"Small","Typo Rate":"10%","Instruction-tuned":"true"}. This record does not assert independent reproduction.

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