Narev
  • Twitter
  • Create

  • Evals
    • Models
    • Hardware

  • Catalog

> Hub > Evals > Models > …

loading run

> Hub > Evals > Models > Polish Language Proficiency Benchmark

Evaluates fundamental and advanced competence in the Polish language across grammar, orthography, vocabulary, idiomatic expressions, and syntax.

Scorer: Factuality

loading chart
Score vs cost per task
#scoremodel
cost
price
ttfttotal tok
190%qwen/qwen3.7-plus
$0.00039
$0.32 / $1.28 per 1M
0.89s366.8
278%mistralai/mistral-small-3.2-24b-instruct
$0.00001
$0.07 / $0.20 per 1M
0.49s100.7
378%anthropic/claude-opus-4.8
$0.00121
$5.00 / $25.00 per 1M
1.10s135.6

Prompts

  • Complete the traditional Polish proverb: 'Gdzie kucharek sześć, tam...' A) smaczny obiad jest B) chl…
  • What does the Polish idiomatic expression 'wiercić komuś dziurę w brzuchu' mean? A) To cause severe …
  • What does the Polish word 'ewentualnie' actually mean in standard Polish? A) Eventually / in the end…
  • What is the correct genitive plural (dopełniacz liczby mnogiej) of the noun 'ręka' in standard Polis…
  • What is the meaning of the Polish verb 'zbić z pantałyku'? A) To construct something hastily B) To c…
  • Which grammatical case is governed by the Polish preposition 'dzięki' (thanks to)? A) Biernik (Accus…
  • Which of the following adverbs is spelled correctly with the negative particle 'nie'? A) Nienajlepie…
  • Which of the following is the perfective (dokonany) aspect counterpart of the imperfective Polish ve…
  • Which of the following Polish words is spelled correctly according to the rules of standard Polish o…
  • Which of the following sentences correctly uses numeral agreement in standard Polish? A) Dwaj bracia…