These items measure proficiency with arithmetic, fractions, percentages, negative numbers, elementary algebra, geometry, averages, and decimals.
Scorer: Factuality
| # | score | model | cost price | ttft | total tok |
|---|---|---|---|---|---|
| 1 | 100% | gpt-5.5-pro | $0.00910 $30.00 / $180.00 per 1M | 1.08s | 99 |
| 2 | 72% | qwen/qwen3.8-2.4t-a95b | $0.00037 $2.00 / $6.00 per 1M | 1.57s | 121.7 |
| 3 | 40% | gpt-5.4-nano | $0.00002 $0.20 / $1.25 per 1M | 0.70s | 63.1 |
Prompts