Narev
  • Twitter
  • Create

  • Evals
    • Models
    • Hardware

  • Catalog

> Hub > Evals > Models > …

loading run

> Hub > Evals > Models > Polish Language Proficiency Benchmark

Comprehensive evaluation benchmark for Polish language proficiency, testing grammatical inflection, plurale tantum numerals, orthographic rules, idiom comprehension, pleonasms, aspectual pairs, punctuation, and cultural knowledge.

Scorer: Factuality

loading chart
Score vs cost per task
#scoremodel
cost
price
ttfttotal tok
180%gpt-5.5
$0.00945
$5.00 / $30.00 per 1M
0.72s351.2
270%mistral-large-2512
$0.00051
$0.50 / $1.50 per 1M
0.88s368.3
360%claude-opus-5
$0.02851
$5.00 / $25.00 per 1M
2.28s1,193.4