Math-PT (pt-BR MC) - Level 3: leaderboard
Metric: Accuracy (%) on the 140 level-3 multiple-choice questions in Brazilian Portuguese (OBMEP); native-language zero-shot prompt asking for a boxed final answer, figures given as LaTeX source; the letter in the final boxed answer must match the key; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 92.86 |
| 2 | Qwen 3 235B A22B | 92.86 |
| 3 | DeepSeek V3.1 | 91.43 |
| 4 | Qwen 3 14B | 90 |
| 5 | Qwen 3 32B | 89.29 |
| 6 | Qwen 3 30B A3B | 89.29 |
| 7 | Gemini 2.5 Flash | 88.57 |
| 8 | Qwen 3 8B | 87.14 |
| 9 | Claude Haiku 4.5 | 84.29 |
| 10 | Gemma 3 27B (IT) | 69.29 |
| 11 | Llama 3.3 70B Instruct | 35 |
Interactive version: theaggregate.ai/benchmark?slug=math-pt-pt-br-mc-level-3 · How It Works · Data refreshed daily, snapshot 2026-10-07.