# Reading Comprehension on Belebele Polish Source: [Reading Comprehension on Belebele Polish]() Collection index: [llms.txt]() Data updated: 2026-04-14T10:46:42.013Z Evaluation of Reading Comprehension performance on the Polish subset of the Belebele dataset. 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 | Reading Comprehension | | Dataset (including any stated split) | Belebele Polish | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 | | --- | --- | --- | --- | | Qwen2.5-14B-Instruct | 87.56 | Not recorded | 69ddca5e7d0172140ec79d89 | | phi-4 | 83 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v3.0-Instruct | 82.11 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-PL-11B-v3.0-Instruct | 81.22 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.6-Instruct | 79.22 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2.5-7B | 79 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-Minitron-7B-v3.0-Instruct | 78.22 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-PL-Minitron-7B-v3.0-Instruct | 77.44 | Not recorded | 69ddca5e7d0172140ec79d89 | | cjvt/GaMS-9B-Instruct | 71.89 | Not recorded | 69ddca5e7d0172140ec79d89 | | Mistral-Nemo-Instruct-2407 | 71.44 | Not recorded | 69ddca5e7d0172140ec79d89 | | EuroLLM-9B-Instruct | 71.22 | Not recorded | 69ddca5e7d0172140ec79d89 | | Apertus-8B-Instruct-2509 | 70 | Not recorded | 69ddca5e7d0172140ec79d89 | | Apertus-8B-2509 | 58.44 | Not recorded | 69ddca5e7d0172140ec79d89 | ### Qwen2.5-14B-Instruct Accuracy: 87.56. Result ID: 69de1b0847f34ce924c6512a. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"14.8"}. This record does not assert independent reproduction. ### phi-4 Accuracy: 83. Result ID: 69de1b0847f34ce924c6512c. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"14.7"}. This record does not assert independent reproduction. ### Bielik-11B-v3.0-Instruct Accuracy: 82.11. Result ID: 69de1b0847f34ce924c6512b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"11.2"}. This record does not assert independent reproduction. ### Bielik-PL-11B-v3.0-Instruct Accuracy: 81.22. Result ID: 69de1b0847f34ce924c6512e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"11.2"}. This record does not assert independent reproduction. ### Bielik-11B-v2.6-Instruct Accuracy: 79.22. Result ID: 69de1b0847f34ce924c65135. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"11.2"}. This record does not assert independent reproduction. ### Qwen2.5-7B Accuracy: 79. Result ID: 69de1b0847f34ce924c6512f. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"7.6"}. This record does not assert independent reproduction. ### Bielik-Minitron-7B-v3.0-Instruct Accuracy: 78.22. Result ID: 69de1b0847f34ce924c6512d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"7.5"}. This record does not assert independent reproduction. ### Bielik-PL-Minitron-7B-v3.0-Instruct Accuracy: 77.44. Result ID: 69de1b0847f34ce924c65130. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"7.5"}. This record does not assert independent reproduction. ### cjvt/GaMS-9B-Instruct Accuracy: 71.89. Result ID: 69de1b0847f34ce924c65132. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"9.2"}. This record does not assert independent reproduction. ### Mistral-Nemo-Instruct-2407 Accuracy: 71.44. Result ID: 69de1b0847f34ce924c65131. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"12.2"}. This record does not assert independent reproduction. ### EuroLLM-9B-Instruct Accuracy: 71.22. Result ID: 69de1b0847f34ce924c65134. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"9.2"}. This record does not assert independent reproduction. ### Apertus-8B-Instruct-2509 Accuracy: 70. Result ID: 69de1b0847f34ce924c65133. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"8.0"}. This record does not assert independent reproduction. ### Apertus-8B-2509 Accuracy: 58.44. Result ID: 69de1b0847f34ce924c65136. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"8.0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.