# Knowledge & Reasoning Evaluation on ARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT (test) Source: [Knowledge & Reasoning Evaluation on ARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT (test)]() Collection index: [llms.txt]() Data updated: 2026-03-05T07:37:32.524Z Evaluation of model performance across a specific test set aggregation of academic benchmarks (MMLU, ARC-Challenge, GSM8K-PT) and Brazilian/Portuguese national exams (ENEM, BLUEX, OAB, BELEBELE). 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 | Post-training Evaluation | | Dataset (including any stated split) | ARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT, IFEval-PT (test) | | Metric | Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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](): Higher is better; unit: PERCENT. - [K&R Score (NPM)](): Higher is better; unit: PERCENT. - [Instruction Tuning Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | Tucano2-qwen-3.7B-Think | 51.27 | Not recorded | 69a90de92d603e6de3e40680 | | SmolLM3-3B | 48.58 | Not recorded | 69a90de92d603e6de3e40680 | | Qwen3-4B | 46.35 | Not recorded | 69a90de92d603e6de3e40680 | | Qwen3-1.7B | 36.54 | Not recorded | 69a90de92d603e6de3e40680 | | Tucano2-qwen-1.5B-Think | 27.54 | Not recorded | 69a90de92d603e6de3e40680 | | Qwen3-0.6B | 24.11 | Not recorded | 69a90de92d603e6de3e40680 | | Tucano2-qwen-0.5B-Think | 14.41 | Not recorded | 69a90de92d603e6de3e40680 | ### Tucano2-qwen-3.7B-Think Average Score: 51.27. Result ID: 69a9329d6dbb7075b95242b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Think"}. This record does not assert independent reproduction. ### SmolLM3-3B Average Score: 48.58. Result ID: 69a9329d6dbb7075b95242b5. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-4B Average Score: 46.35. Result ID: 69a9329d6dbb7075b95242b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-1.7B Average Score: 36.54. Result ID: 69a9329d6dbb7075b95242b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Tucano2-qwen-1.5B-Think Average Score: 27.54. Result ID: 69a9329d6dbb7075b95242b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Think"}. This record does not assert independent reproduction. ### Qwen3-0.6B Average Score: 24.11. Result ID: 69a9329d6dbb7075b95242b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Tucano2-qwen-0.5B-Think Average Score: 14.41. Result ID: 69a9329d6dbb7075b95242ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"variant":"Think"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.