Open LLM Leaderboard
English benchmark suite of ARC challenge, HellaSwag, WinoGrande, TruthfulQA, MMLU and GSM8K.
Key open_llm_leaderboard · version 3802da7d-eac8-4a84-b3ca-b1d8c2e12196
Cited claim · P28 · Author-curated
On the English Open LLM Leaderboard average, Bielik-PL-11B-v3.0-Instruct scores 71.49 and Bielik-11B-v3.0-Instruct 72.45.
Structured assertion
Relation: Metric comparison
- benchmark
- Open LLM LeaderboardBenchmark the values are reported on.
- metric
- averageScore reported on the benchmark.
- language
- EnglishLanguage of the evaluated tasks.
- subject
- Bielik-PL-11B-v3.0-InstructModel or tokenizer after the tokenizer change.
- subject value
- 71.49 scoreValue of the metric for the subject.
- comparator
- Bielik-11B-v3.0-InstructModel or tokenizer before the tokenizer change.
- comparator value
- 72.45 scoreValue of the metric for the comparator.
Paper citations
arXiv:2604.10799v1 →Revision supplied by author
Bielik-11B-v3.0-Instruct scores 72.45 average, with particularly strong performance on GSM8K (85.60) and ARC challenge (64.59), indicating robust mathematical and reasoning capabilities.
The Polish tokenizer variants achieve 71.49 (Bielik-PL-11B-v3.0-Instruct) and 67.63 (Bielik-PL-Minitron-7B-v3.0-Instruct) on the same Open LLM Leaderboard aggregate.
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
English
The English language.
Key english · version 86acabda-0237-47be-8e26-a81500c184aa
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.