# Polish Board Certification Examinations on speakleash/PES 2018-2022 Source: [Polish Board Certification Examinations on speakleash/PES 2018-2022]() Collection index: [llms.txt]() Data updated: 2026-04-14T10:46:42.039Z Evaluation of model performance on the Polish Board Certification Examinations dataset (speakleash/PES 2018-2022), typically measured by average percentage score. 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 | Polish Board Certification Examinations | | Dataset (including any stated split) | speakleash/PES 2018-2022 | | Metric | Average Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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. ## Recorded results | Method | Average Score | Result date | Report paper | | --- | --- | --- | --- | | Meta-Llama-3.1-405B-Instruct-FP8 | 69.2 | Not recorded | 69ddca5e7d0172140ec79d89 | | Mistral-Large-Instruct-2407† | 64.28 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2.5-72B-Instruct | 63.89 | Not recorded | 69ddca5e7d0172140ec79d89 | | Meta-Llama-3.1-70B-Instruct | 61.75 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2-72B-Instruct | 61.35 | Not recorded | 69ddca5e7d0172140ec79d89 | | Meta-Llama-3-70B-Instruct | 57.51 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2.5-32B | 55.69 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2.5-32B-Instruct | 54.52 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v3.0-Instruct | 50.21 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2.5-14B-Instruct | 49.6 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-PL-11B-v3.0-Instruct | 48.42 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v3-Base-20250730 | 45.86 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.6-Instruct | 44.88 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.5-Instruct | 44.85 | Not recorded | 69ddca5e7d0172140ec79d89 | | GLM-4-9b-chat | 44.54 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-Minitron-7B-v3.0-Instruct | 44.36 | Not recorded | 69ddca5e7d0172140ec79d89 | | Mistral-Small-Instruct-2409 | 43.6 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-4.5B-v3.0-Instruct | 43.55 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-PL-Minitron-7B-v3.0-Instruct | 43.35 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.3-Instruct | 43.26 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.1-Instruct | 43.16 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.2-Instruct | 43.05 | Not recorded | 69ddca5e7d0172140ec79d89 | | Qwen2.5-7B-Instruct | 42.69 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2.0-Instruct | 41.53 | Not recorded | 69ddca5e7d0172140ec79d89 | | Meta-Llama-3.1-8B-Instruct | 40.6 | Not recorded | 69ddca5e7d0172140ec79d89 | | Mistral-Nemo-Instruct-2407 | 40.36 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-11B-v2 | 39.98 | Not recorded | 69ddca5e7d0172140ec79d89 | | PLLuM-12B-nc-chat-250715† | 38.53 | Not recorded | 69ddca5e7d0172140ec79d89 | | PLLuM-12B-chat | 36.51 | Not recorded | 69ddca5e7d0172140ec79d89 | | EuroLLM-9B-Instruct | 35.96 | Not recorded | 69ddca5e7d0172140ec79d89 | | Mistral-7B-Instruct-v0.3 | 31.24 | Not recorded | 69ddca5e7d0172140ec79d89 | | Bielik-7B-Instruct-v0.1 | 29.74 | Not recorded | 69ddca5e7d0172140ec79d89 | ### Meta-Llama-3.1-405B-Instruct-FP8 Average Score: 69.2. Result ID: 69de1b0847f34ce924c651c5. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"405.0","Setting":"5-shot"}. This record does not assert independent reproduction. ### Mistral-Large-Instruct-2407† Average Score: 64.28. Result ID: 69de1b0847f34ce924c651c6. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"123.0","Setting":"5-shot"}. This record does not assert independent reproduction. ### Qwen2.5-72B-Instruct Average Score: 63.89. Result ID: 69de1b0847f34ce924c651c7. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"72.7","Setting":"5-shot"}. This record does not assert independent reproduction. ### Meta-Llama-3.1-70B-Instruct Average Score: 61.75. Result ID: 69de1b0847f34ce924c651c8. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"70.6","Setting":"5-shot"}. This record does not assert independent reproduction. ### Qwen2-72B-Instruct Average Score: 61.35. Result ID: 69de1b0847f34ce924c651c9. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"72.7","Setting":"5-shot"}. This record does not assert independent reproduction. ### Meta-Llama-3-70B-Instruct Average Score: 57.51. Result ID: 69de1b0847f34ce924c651ca. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"70.6","Setting":"5-shot"}. This record does not assert independent reproduction. ### Qwen2.5-32B Average Score: 55.69. Result ID: 69de1b0847f34ce924c651cb. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"32.8","Setting":"5-shot"}. This record does not assert independent reproduction. ### Qwen2.5-32B-Instruct Average Score: 54.52. Result ID: 69de1b0847f34ce924c651cc. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"32.8","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v3.0-Instruct Average Score: 50.21. Result ID: 69de1b0847f34ce924c651cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Qwen2.5-14B-Instruct Average Score: 49.6. Result ID: 69de1b0847f34ce924c651ce. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"14.8","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-PL-11B-v3.0-Instruct Average Score: 48.42. Result ID: 69de1b0847f34ce924c651cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v3-Base-20250730 Average Score: 45.86. Result ID: 69de1b0847f34ce924c651d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v2.6-Instruct Average Score: 44.88. Result ID: 69de1b0847f34ce924c651d1. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v2.5-Instruct Average Score: 44.85. Result ID: 69de1b0847f34ce924c651d2. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### GLM-4-9b-chat Average Score: 44.54. Result ID: 69de1b0847f34ce924c651d3. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"9.0","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-Minitron-7B-v3.0-Instruct Average Score: 44.36. Result ID: 69de1b0847f34ce924c651d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"7.5","Setting":"5-shot"}. This record does not assert independent reproduction. ### Mistral-Small-Instruct-2409 Average Score: 43.6. Result ID: 69de1b0847f34ce924c651d5. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"22.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-4.5B-v3.0-Instruct Average Score: 43.55. Result ID: 69de1b0847f34ce924c651d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"4.8","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-PL-Minitron-7B-v3.0-Instruct Average Score: 43.35. Result ID: 69de1b0847f34ce924c651d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"7.5","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v2.3-Instruct Average Score: 43.26. Result ID: 69de1b0847f34ce924c651d8. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v2.1-Instruct Average Score: 43.16. Result ID: 69de1b0847f34ce924c651d9. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v2.2-Instruct Average Score: 43.05. Result ID: 69de1b0847f34ce924c651da. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Average Score: 42.69. Result ID: 69de1b0847f34ce924c651db. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"7.6","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v2.0-Instruct Average Score: 41.53. Result ID: 69de1b0847f34ce924c651dc. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Meta-Llama-3.1-8B-Instruct Average Score: 40.6. Result ID: 69de1b0847f34ce924c651dd. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"8.0","Setting":"5-shot"}. This record does not assert independent reproduction. ### Mistral-Nemo-Instruct-2407 Average Score: 40.36. Result ID: 69de1b0847f34ce924c651de. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"12.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-11B-v2 Average Score: 39.98. Result ID: 69de1b0847f34ce924c651df. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"11.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### PLLuM-12B-nc-chat-250715† Average Score: 38.53. Result ID: 69de1b0847f34ce924c651e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"12.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### PLLuM-12B-chat Average Score: 36.51. Result ID: 69de1b0847f34ce924c651e1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"12.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### EuroLLM-9B-Instruct Average Score: 35.96. Result ID: 69de1b0847f34ce924c651e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters (B)":"9.2","Setting":"5-shot"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct-v0.3 Average Score: 31.24. Result ID: 69de1b0847f34ce924c651e3. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"7.0","Setting":"5-shot"}. This record does not assert independent reproduction. ### Bielik-7B-Instruct-v0.1 Average Score: 29.74. Result ID: 69de1b0847f34ce924c651e4. [Reporting paper]() Recorded evaluation configuration: {"Parameters (B)":"7.2","Setting":"5-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.