# Reading Comprehension on Belebele 28 European languages Source: [Reading Comprehension on Belebele 28 European languages]() Collection index: [llms.txt]() Data updated: 2026-04-14T10:46:42.396Z Evaluation of Reading Comprehension performance specifically on the subset of 28 European languages within 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 28 European languages | | Metric | Overall Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 34 of 34 | | 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 - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Score | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-14B-Instruct | 85.91 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | Qwen2.5-14B-Instruct | 85.91 | Not recorded | 69b39a250636e5bf4afbcb7f | | Qwen2.5-14B-Instruct | 85.91 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v3.0-Instruct | 82.98 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | Bielik-11B-v3.0-Instruct | 82.98 | Not recorded | 69b39a250636e5bf4afbcb7f | | Bielik-11B-v3.0-Instruct | 82.98 | Not recorded | 69ddca5e7d0172140ec79d89 | | phi-4 | 81.71 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | phi-4 | 81.71 | Not recorded | 69b39a250636e5bf4afbcb7f | | phi-4 | 81.71 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-Minitron-7B-v3.0-Instruct | 78.03 | Not recorded | 69b39a250636e5bf4afbcb7f | | Bielik-Minitron-7B-v3.0-Instruct | 78.03 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-PL-11B-v3.0-Instruct | 77.41 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2.5-7B | 74.6 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | Qwen2.5-7B | 74.6 | Not recorded | 69b39a250636e5bf4afbcb7f | | Qwen2.5-7B | 74.6 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-PL-Minitron-7B-v3.0-Instruct | 74.23 | Not recorded | 69ddca5e7d0172140ec79d89 | | Mistral-Nemo-Instruct-2407 | 74.14 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | Mistral-Nemo-Instruct-2407 | 74.14 | Not recorded | 69b39a250636e5bf4afbcb7f | | Mistral-Nemo-Instruct-2407 | 74.14 | Not recorded | 69ddca5e7d0172140ec79d89 | | cjvt/GaMS-9B-Instruct | 72.4 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | cjvt/GaMS-9B-Instruct | 72.4 | Not recorded | 69b39a250636e5bf4afbcb7f | | cjvt/GaMS-9B-Instruct | 72.4 | Not recorded | 69ddca5e7d0172140ec79d89 | | Apertus-8B-Instruct-2509 | 69.58 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | Apertus-8B-Instruct-2509 | 69.58 | Not recorded | 69b39a250636e5bf4afbcb7f | | Apertus-8B-Instruct-2509 | 69.58 | Not recorded | 69ddca5e7d0172140ec79d89 | | EuroLLM-9B-Instruct | 69.05 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | EuroLLM-9B-Instruct | 69.05 | Not recorded | 69b39a250636e5bf4afbcb7f | | EuroLLM-9B-Instruct | 69.05 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.6-Instruct | 68.67 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | Bielik-11B-v2.6-Instruct | 68.67 | Not recorded | 69b39a250636e5bf4afbcb7f | | Bielik-11B-v2.6-Instruct | 68.67 | Not recorded | 69ddca5e7d0172140ec79d89 | | Apertus-8B-2509 | 59.04 | Not recorded | 69705d7ce25ad2fa9d1ecfbf | | Apertus-8B-2509 | 59.04 | Not recorded | 69b39a250636e5bf4afbcb7f | | Apertus-8B-2509 | 59.04 | Not recorded | 69ddca5e7d0172140ec79d89 | ### Qwen2.5-14B-Instruct Overall Score: 85.91. Result ID: 6996a9a35698665ec4f38a29. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"14"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct Overall Score: 85.91. Result ID: 69b3d2cc47f34ce9249e1e5c. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"14"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct Overall Score: 85.91. Result ID: 69de1b0847f34ce924c6511d. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"14.8"}. This record does not assert independent reproduction. ### Bielik-11B-v3.0-Instruct Overall Score: 82.98. Result ID: 6996a9a35698665ec4f38a2a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"11"}. This record does not assert independent reproduction. ### Bielik-11B-v3.0-Instruct Overall Score: 82.98. Result ID: 69b3d2cc47f34ce9249e1e5d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"11"}. This record does not assert independent reproduction. ### Bielik-11B-v3.0-Instruct Overall Score: 82.98. Result ID: 69de1b0847f34ce924c6511e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"11.2"}. This record does not assert independent reproduction. ### phi-4 Overall Score: 81.71. Result ID: 6996a9a35698665ec4f38a2b. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"15"}. This record does not assert independent reproduction. ### phi-4 Overall Score: 81.71. Result ID: 69b3d2cc47f34ce9249e1e5e. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"15"}. This record does not assert independent reproduction. ### phi-4 Overall Score: 81.71. Result ID: 69de1b0847f34ce924c6511f. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"14.7"}. This record does not assert independent reproduction. ### Bielik-Minitron-7B-v3.0-Instruct Overall Score: 78.03. Result ID: 69b3d2cc47f34ce9249e1e5f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"7"}. This record does not assert independent reproduction. ### Bielik-Minitron-7B-v3.0-Instruct Overall Score: 78.03. Result ID: 69de1b0847f34ce924c65120. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"7.5"}. This record does not assert independent reproduction. ### Bielik-PL-11B-v3.0-Instruct Overall Score: 77.41. Result ID: 69de1b0847f34ce924c65121. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"11.2"}. This record does not assert independent reproduction. ### Qwen2.5-7B Overall Score: 74.6. Result ID: 6996a9a35698665ec4f38a2c. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"7"}. This record does not assert independent reproduction. ### Qwen2.5-7B Overall Score: 74.6. Result ID: 69b3d2cc47f34ce9249e1e60. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"7"}. This record does not assert independent reproduction. ### Qwen2.5-7B Overall Score: 74.6. Result ID: 69de1b0847f34ce924c65122. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"7.6"}. This record does not assert independent reproduction. ### Bielik-PL-Minitron-7B-v3.0-Instruct Overall Score: 74.23. Result ID: 69de1b0847f34ce924c65123. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"7.5"}. This record does not assert independent reproduction. ### Mistral-Nemo-Instruct-2407 Overall Score: 74.14. Result ID: 6996a9a35698665ec4f38a2d. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"12"}. This record does not assert independent reproduction. ### Mistral-Nemo-Instruct-2407 Overall Score: 74.14. Result ID: 69b3d2cc47f34ce9249e1e61. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"12"}. This record does not assert independent reproduction. ### Mistral-Nemo-Instruct-2407 Overall Score: 74.14. Result ID: 69de1b0847f34ce924c65124. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"12.2"}. This record does not assert independent reproduction. ### cjvt/GaMS-9B-Instruct Overall Score: 72.4. Result ID: 6996a9a35698665ec4f38a2e. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"9"}. This record does not assert independent reproduction. ### cjvt/GaMS-9B-Instruct Overall Score: 72.4. Result ID: 69b3d2cc47f34ce9249e1e62. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"9"}. This record does not assert independent reproduction. ### cjvt/GaMS-9B-Instruct Overall Score: 72.4. Result ID: 69de1b0847f34ce924c65125. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"9.2"}. This record does not assert independent reproduction. ### Apertus-8B-Instruct-2509 Overall Score: 69.58. Result ID: 6996a9a35698665ec4f38a2f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"8"}. This record does not assert independent reproduction. ### Apertus-8B-Instruct-2509 Overall Score: 69.58. Result ID: 69b3d2cc47f34ce9249e1e63. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"8"}. This record does not assert independent reproduction. ### Apertus-8B-Instruct-2509 Overall Score: 69.58. Result ID: 69de1b0847f34ce924c65126. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"8.0"}. This record does not assert independent reproduction. ### EuroLLM-9B-Instruct Overall Score: 69.05. Result ID: 6996a9a35698665ec4f38a30. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"9"}. This record does not assert independent reproduction. ### EuroLLM-9B-Instruct Overall Score: 69.05. Result ID: 69b3d2cc47f34ce9249e1e64. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"9"}. This record does not assert independent reproduction. ### EuroLLM-9B-Instruct Overall Score: 69.05. Result ID: 69de1b0847f34ce924c65127. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"9.2"}. This record does not assert independent reproduction. ### Bielik-11B-v2.6-Instruct Overall Score: 68.67. Result ID: 6996a9a35698665ec4f38a31. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"11"}. This record does not assert independent reproduction. ### Bielik-11B-v2.6-Instruct Overall Score: 68.67. Result ID: 69b3d2cc47f34ce9249e1e65. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"11"}. This record does not assert independent reproduction. ### Bielik-11B-v2.6-Instruct Overall Score: 68.67. Result ID: 69de1b0847f34ce924c65128. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"11.2"}. This record does not assert independent reproduction. ### Apertus-8B-2509 Overall Score: 59.04. Result ID: 6996a9a35698665ec4f38a32. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params (B)":"8"}. This record does not assert independent reproduction. ### Apertus-8B-2509 Overall Score: 59.04. Result ID: 69b3d2cc47f34ce9249e1e66. [Reporting paper]() Recorded evaluation configuration: {"Params (B)":"8"}. This record does not assert independent reproduction. ### Apertus-8B-2509 Overall Score: 59.04. Result ID: 69de1b0847f34ce924c65129. [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.