Cited claim

Sign in with GitHub
← Publications

Cited claim · P33 · Author-curated

On CPTUB tricky questions, Bielik-PL-11B-v3.0-Instruct scores 3.13 and Bielik-11B-v3.0-Instruct 3.19.

Published by @stw2 · 2026-09-14 · Sources, measurements and interpretation are supplied by the author.

Structured assertion

Relation: Metric comparison

benchmark
CPTUBBenchmark the values are reported on.
scope
tricky questions componentPart of the benchmark the value covers.
language
PolishLanguage of the evaluated tasks.
subject
Bielik-PL-11B-v3.0-InstructModel or tokenizer after the tokenizer change.
subject value
3.13 scoreValue of the metric for the subject.
comparator
Bielik-11B-v3.0-InstructModel or tokenizer before the tokenizer change.
comparator value
3.19 scoreValue of the metric for the comparator.

Paper citations

arXiv:2604.10799v1 →Revision supplied by author

  1. Table 4, p. 9, Tricky Questions column, row Bielik-PL-11B-v3.0-Instruct (3.13)

  2. Section 5.3, p. 10

    The tricky questions component yields a score of 3.19, reflecting the challenging nature of these adversarial queries.

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

Concept JSON · Defining publication

CPTUB

Complex Polish Text Understanding Benchmark: implicatures and tricky questions, probing inference from context, pragmatic understanding and reasoning under ambiguity.

Key cptub · version 79fea33d-768f-40c3-a531-6996ff58b1ad

Concept JSON · Defining publication

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

Concept JSON · Defining publication

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

Concept JSON · Defining publication