# STEM Question Answering on ARC-C 24 official EU languages Source: [STEM Question Answering on ARC-C 24 official EU languages]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:03:50.537Z Evaluation of model performance on the Abstract Reasoning Corpus (ARC-C) subset comprising the 24 official European Union languages, focusing on STEM Question Answering. 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 Question Answering | | Dataset (including any stated split) | ARC-C 24 official EU languages | | Metric | Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Score | Result date | Report paper | | --- | --- | --- | --- | | Qwen-3-32B | 93.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Qwen-3-30B-A3B | 93.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Llama-3.3-70B | 91.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Gemma-3-27B | 90.8 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Qwen-3-14B | 90.5 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Mistral-3.2-24B | 90 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Gemma-3-12B | 87.9 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | EuroLLM-22B | 84.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | EuroLLM-9B | 80.7 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | OLMo-3.1-32B | 79.8 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Apertus-70B | 79.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Apertus-8B | 71 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | Llama-3.1-8B | 69 | Not recorded | 698575d8c97a0b3e3b5d5e8c | | OLMo-3-7B | 54.5 | Not recorded | 698575d8c97a0b3e3b5d5e8c | ### Qwen-3-32B Score: 93.1. Result ID: 699647a15698665ec48b9a21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### Qwen-3-30B-A3B Score: 93.1. Result ID: 699647a15698665ec48b9a22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### Llama-3.3-70B Score: 91.1. Result ID: 699647a15698665ec48b9a1d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### Gemma-3-27B Score: 90.8. Result ID: 699647a15698665ec48b9a1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### Qwen-3-14B Score: 90.5. Result ID: 699647a15698665ec48b9a20. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### Mistral-3.2-24B Score: 90. Result ID: 699647a15698665ec48b9a1b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"European"}. This record does not assert independent reproduction. ### Gemma-3-12B Score: 87.9. Result ID: 699647a15698665ec48b9a1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### EuroLLM-22B Score: 84.1. Result ID: 699647a15698665ec48b9a16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Fully-open","Regional origin":"European"}. This record does not assert independent reproduction. ### EuroLLM-9B Score: 80.7. Result ID: 699647a15698665ec48b9a15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Fully-open","Regional origin":"European"}. This record does not assert independent reproduction. ### OLMo-3.1-32B Score: 79.8. Result ID: 699647a15698665ec48b9a1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Fully-open","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### Apertus-70B Score: 79.6. Result ID: 699647a15698665ec48b9a18. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Fully-open","Regional origin":"European"}. This record does not assert independent reproduction. ### Apertus-8B Score: 71. Result ID: 699647a15698665ec48b9a17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Fully-open","Regional origin":"European"}. This record does not assert independent reproduction. ### Llama-3.1-8B Score: 69. Result ID: 699647a15698665ec48b9a1c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Weights accessibility":"Open-weights","Regional origin":"Non-European"}. This record does not assert independent reproduction. ### OLMo-3-7B Score: 54.5. Result ID: 699647a15698665ec48b9a19. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Weights accessibility":"Fully-open","Regional origin":"Non-European"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.