Evaluates foundational mathematical problem-solving skills across arithmetic, fractions, percentages, basic algebra, proportions, and elementary geometry.
Scorer: Factuality
| # | score | model | cost price | ttft | total tok |
|---|---|---|---|---|---|
| 1 | 86% | gemini-3.1-flash-lite | $0.00005 $0.25 / $1.50 per 1M | 0.77s | 96.4 |
| 2 | 84% | qwen/qwen3.5-9b | $0.00012 $0.10 / $0.15 per 1M | 1.85s | 846.3 |
| 3 | 60% | gpt-5.4-nano | $0.00002 $0.20 / $1.25 per 1M | 0.64s | 78 |
Prompts