Evaluates proficiency in the Polish language across complex grammar, noun/adjective declension, verbal aspect, orthography, false friends, and idioms.
Scorer: Factuality
| # | score | model | cost price | ttft | total tok |
|---|---|---|---|---|---|
| 1 | 100% | qwen/qwen3.8-max | $0.00125 $2.00 / $6.00 per 1M | 1.48s | 291.6 |
| 2 | 90% | mistral-small-2603 | $0.00001 $0.15 / $0.60 per 1M | 0.38s | 92.4 |
| 3 | failed | anthropic/claude-opus-5-fast | — $10.00 / $50.00 per 1M | — | 0 |
Prompts