Evaluates model factual accuracy, depth, and precision across key historical periods of Sweden, including the Kalmar Union, the Swedish Empire (Stormaktstiden), the Napoleonic Era, and 20th-century modern state development.
Scorer: Factuality
| # | score | model | cost price | ttft | total tok |
|---|---|---|---|---|---|
| 1 | 60% | mistral-large-2512 | $0.00052 $0.50 / $1.50 per 1M | 1.19s | 371 |
| 2 | 52% | gpt-5.5-pro | $0.06376 $30.00 / $180.00 per 1M | 0.58s | 384.9 |
| 3 | failed | anthropic/claude-opus-5 | — $5.00 / $25.00 per 1M | — | 0 |
Prompts