Evaluates model factual accuracy and depth of knowledge regarding key events, figures, and eras in Polish history spanning from the Middle Ages to the democratic transition.
Scorer: Factuality
| # | score | model | cost price | ttft | total tok |
|---|---|---|---|---|---|
| 1 | 72% | gpt-5.5 | $0.00292 $5.00 / $30.00 per 1M | 0.44s | 127 |
| 2 | 66% | qwen/qwen3.8-max | $0.00127 $2.00 / $6.00 per 1M | 1.33s | 264 |
| 3 | 60% | claude-opus-5 | $0.02508 $5.00 / $25.00 per 1M | 1.37s | 1,046.2 |
Prompts