Evaluates an LLM's ability to generate genuinely humorous, culturally attuned, and linguistically natural jokes and puns in Polish.
Scorer: Humor
| # | score | model | cost price | ttft | total tok |
|---|---|---|---|---|---|
| 1 | 100% | mistral-large-2512 | $0.00077 $0.50 / $1.50 per 1M | 0.57s | 537.5 |
| 2 | 100% | claude-sonnet-5 | $0.00537 $2.00 / $10.00 per 1M | 1.43s | 578.9 |
| 3 | 100% | gpt-5.5 | $0.00649 $5.00 / $30.00 per 1M | 0.64s | 247.7 |
Prompts