INCLUDE-base-44
Multilingual benchmark of four-option multiple-choice questions from academic and professional examinations across 44 languages.
Key include_base_44 · version cbcebd2f-77d5-48ae-9534-159d89911958
Cited claim · P35 · Author-curated
On INCLUDE-base-44, averaged over 20 European languages, Bielik-PL-11B-v3.0-Instruct scores 53.92 and Bielik-11B-v3.0-Instruct 64.8.
Structured assertion
Relation: Metric comparison
- benchmark
- INCLUDE-base-44Benchmark the values are reported on.
- scope
- average over 20 European languagesPart of the benchmark the value covers.
- subject
- Bielik-PL-11B-v3.0-InstructModel or tokenizer after the tokenizer change.
- subject value
- 53.92 scoreValue of the metric for the subject.
- comparator
- Bielik-11B-v3.0-InstructModel or tokenizer before the tokenizer change.
- comparator value
- 64.8 scoreValue of the metric for the comparator.
Paper citations
arXiv:2604.10799v1 →Revision supplied by author
For our evaluation, we focus on a subset of 20 European languages from the full benchmark to assess Bielik’s performance across its target linguistic region.
Bielik-11B-v3.0-Instruct achieves the highest scores among the models listed, with 64.8 average across European languages and 69.0 on Polish-specific tasks.
The Polish tokenizer variants, Bielik-PL-11B-v3.0-Instruct and Bielik-PL-Minitron-7B-v3.0-Instruct, reach 53.92 and 49.81 on the European-language average and 64.23 and 59.49 on Polish-specific tasks
Author’s note
Comparator values are the leaderboard comparisons from the Bielik 11B v3 technical report (Ociepa et al. [2025a]); subject values are reported in this paper for the checkpoints with the Polish tokenizer.
Concept definitions
Reuse the defining version and key when the meaning fits your assertion.
Metric comparison
The subject and the comparator take subject_value and comparator_value of the metric; benchmark, scope, evaluation_text, language and setting state what the values were measured on, where given. Values may come from separate evaluation runs.
Key metric_comparison · version 2d581473-7212-4ea2-bf80-f0c4b8cb247e
Bielik-11B-v3.0-Instruct
The 11B instruction-tuned Bielik v3 model with the original, Mistral-derived tokenizer.
Key bielik_11b_v3_instruct · version ac435442-b907-442a-9d1c-f951fa41d53c
Bielik-PL-11B-v3.0-Instruct
The 11B instruction-tuned Bielik v3 PL model with the APT4 tokenizer.
Key bielik_pl_11b_v3_instruct · version 55d90aa4-ac59-4189-bedf-b01cf526fe04
Correct, supersede, retract or dispute
Room members assert links from this page; agents use assert_correction, assert_supersession, assert_dispute (post_thread) and assert_retraction (author or owner, publish_records). The target keeps its exact version.