# Science Question Answering on ARC-C non-EU languages (test)

Source: [Science Question Answering on ARC-C non-EU languages (test)](<https://www.sota2.com/research/sota/science-question-answering-on-arc-c-non-eu-languages-test>)

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

Data updated: 2026-02-26T05:30:51.375Z

Evaluation of model performance on the test split of the ARC-C dataset, specifically filtered for non-European Union 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 | Science Question Answering |
| Dataset (including any stated split) | ARC-C 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/science-question-answering-on-arc-c-non-eu-languages-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen-3-32B | 91.5 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Qwen-3-30B-A3B | 90.8 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Qwen-3-14B | 88.8 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Gemma-3-27B | 88.7 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Llama-3.3-70B | 88.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Mistral-3.2-24B | 87.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Gemma-3-12B | 85.7 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-22B (new) | 79.8 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| OLMo-3.1-32B | 77.3 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-9B (new) | 77.2 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Apertus-70B | 76.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-22B (old) | 76.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-9B (old) | 69.5 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Apertus-8B | 67.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Llama-3.1-8B | 66.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| OLMo-3-7B | 54.7 | Not recorded | 698575d8c97a0b3e3b5d5e8c |

### Qwen-3-32B

Accuracy: 91.5. Result ID: 699647a15698665ec48b991f.

[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: 90.8. Result ID: 699647a15698665ec48b9920.

[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-3-14B

Accuracy: 88.8. Result ID: 699647a15698665ec48b991e.

[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.

### Gemma-3-27B

Accuracy: 88.7. Result ID: 699647a15698665ec48b991d.

[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.

### Llama-3.3-70B

Accuracy: 88.1. Result ID: 699647a15698665ec48b991b.

[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.

### Mistral-3.2-24B

Accuracy: 87.6. Result ID: 699647a15698665ec48b9919.

[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-3-12B

Accuracy: 85.7. Result ID: 699647a15698665ec48b991c.

[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: 79.8. Result ID: 699647a15698665ec48b9914.

[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-3.1-32B

Accuracy: 77.3. Result ID: 699647a15698665ec48b9918.

[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.

### EuroLLM-9B (new)

Accuracy: 77.2. Result ID: 699647a15698665ec48b9912.

[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-70B

Accuracy: 76.6. Result ID: 699647a15698665ec48b9916.

[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.

### EuroLLM-22B (old)

Accuracy: 76.1. Result ID: 699647a15698665ec48b9913.

[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: 69.5. Result ID: 699647a15698665ec48b9911.

[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: 67.6. Result ID: 699647a15698665ec48b9915.

[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: 66.4. Result ID: 699647a15698665ec48b991a.

[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.

### OLMo-3-7B

Accuracy: 54.7. Result ID: 699647a15698665ec48b9917.

[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.

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