# Question Answering on ARC-Hard chat (Māori) Source: [Question Answering on ARC-Hard chat (Māori)]() Collection index: [llms.txt]() Data updated: 2026-02-27T10:47:28.091Z Evaluation of model performance on the Māori language version of the ARC-Hard chat dataset for Question Answering, typically measured by Accuracy. 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 | Question Answering | | Dataset (including any stated split) | ARC-Hard chat (Māori) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BYOL-mri (12B-M) | 59.22 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | BYOL-mri (4B-M) | 51.11 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | Gemma-3 (27B-IT) | 49.66 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | Gemma-3 (12B-IT) | 43.09 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | Gemma-3 (4B-IT) | 37.5 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | Qwen-3 (14B) | 35.75 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | Qwen-3 (8B) | 34.04 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | GPT-OSS (20B) | 32.85 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | Llama-3.1 (Instruct-8B) | 31.91 | Not recorded | 696dba82e25ad2fa9d1eccb7 | | Apertus (8B-Inst-2509) | 27.3 | Not recorded | 696dba82e25ad2fa9d1eccb7 | ### BYOL-mri (12B-M) Accuracy: 59.22. Result ID: 69a1763c35dfcabb00e732ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"12B+ Models"}. This record does not assert independent reproduction. ### BYOL-mri (4B-M) Accuracy: 51.11. Result ID: 69a1763c35dfcabb00e732a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"4B-8B Models"}. This record does not assert independent reproduction. ### Gemma-3 (27B-IT) Accuracy: 49.66. Result ID: 69a1763c35dfcabb00e732ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"12B+ Models"}. This record does not assert independent reproduction. ### Gemma-3 (12B-IT) Accuracy: 43.09. Result ID: 69a1763c35dfcabb00e732ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"12B+ Models"}. This record does not assert independent reproduction. ### Gemma-3 (4B-IT) Accuracy: 37.5. Result ID: 69a1763c35dfcabb00e732a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"4B-8B Models"}. This record does not assert independent reproduction. ### Qwen-3 (14B) Accuracy: 35.75. Result ID: 69a1763c35dfcabb00e732a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"12B+ Models"}. This record does not assert independent reproduction. ### Qwen-3 (8B) Accuracy: 34.04. Result ID: 69a1763c35dfcabb00e732a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"4B-8B Models"}. This record does not assert independent reproduction. ### GPT-OSS (20B) Accuracy: 32.85. Result ID: 69a1763c35dfcabb00e732aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"12B+ Models"}. This record does not assert independent reproduction. ### Llama-3.1 (Instruct-8B) Accuracy: 31.91. Result ID: 69a1763c35dfcabb00e732a4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"4B-8B Models"}. This record does not assert independent reproduction. ### Apertus (8B-Inst-2509) Accuracy: 27.3. Result ID: 69a1763c35dfcabb00e732a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Zero-shot":"true","Instruction-tuned":"true","Model scale category":"4B-8B Models"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.