# Mathematical Reasoning on MGSM non-EU languages (test)

Source: [Mathematical Reasoning on MGSM non-EU languages (test)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mgsm-non-eu-languages-test>)

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

Data updated: 2026-02-26T05:30:51.391Z

Evaluation of model performance on mathematical reasoning problems using the test split of the MGSM dataset, restricted to non-European languages.

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 | Mathematical Reasoning |
| Dataset (including any stated split) | MGSM non-EU languages (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-mgsm-non-eu-languages-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen-3-32B | 91.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Llama-3.3-70B | 90.3 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Qwen-3-14B | 89.8 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Qwen-3-30B-A3B | 89.7 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Mistral-3.2-24B | 88.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Gemma-3-27B | 87 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| OLMo-3.1-32B | 86 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Gemma-3-12B | 84.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-22B (new) | 74.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| OLMo-3-7B | 72.7 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Apertus-70B | 71.9 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Llama-3.1-8B | 70.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-22B (old) | 69.9 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-9B (new) | 63.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-9B (old) | 59.2 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Apertus-8B | 56.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |

### Qwen-3-32B

Accuracy: 91.4. Result ID: 699647a15698665ec48b992f.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

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

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Llama-3.3-70B

Accuracy: 90.3. Result ID: 699647a15698665ec48b992b.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Qwen-3-14B

Accuracy: 89.8. Result ID: 699647a15698665ec48b992e.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

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

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Qwen-3-30B-A3B

Accuracy: 89.7. Result ID: 699647a15698665ec48b9930.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

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

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Mistral-3.2-24B

Accuracy: 88.4. Result ID: 699647a15698665ec48b9929.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"European"}. This record does not assert independent reproduction.

### Gemma-3-27B

Accuracy: 87. Result ID: 699647a15698665ec48b992d.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

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

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### OLMo-3.1-32B

Accuracy: 86. Result ID: 699647a15698665ec48b9928.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694238e845614693628503e0.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Gemma-3-12B

Accuracy: 84.6. Result ID: 699647a15698665ec48b992c.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

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

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### EuroLLM-22B (new)

Accuracy: 74.4. Result ID: 699647a15698665ec48b9924.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### OLMo-3-7B

Accuracy: 72.7. Result ID: 699647a15698665ec48b9927.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694238e845614693628503e0.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Apertus-70B

Accuracy: 71.9. Result ID: 699647a15698665ec48b9926.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885c7.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### Llama-3.1-8B

Accuracy: 70.4. Result ID: 699647a15698665ec48b992a.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### EuroLLM-22B (old)

Accuracy: 69.9. Result ID: 699647a15698665ec48b9923.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### EuroLLM-9B (new)

Accuracy: 63.6. Result ID: 699647a15698665ec48b9922.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### EuroLLM-9B (old)

Accuracy: 59.2. Result ID: 699647a15698665ec48b9921.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### Apertus-8B

Accuracy: 56.4. Result ID: 699647a15698665ec48b9925.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885c7.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

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