Math-PT (pt-BR MC) - Level 2: leaderboard
Math-PT (2026) tests mathematical reasoning on problems written natively in Brazilian Portuguese; this board covers the level-2 multiple-choice questions from OBMEP. Accuracy in percent on the boxed answer letter, higher is better.
Metric: Accuracy (%) on the 118 level-2 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: Not forecast. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 90.68 | #185 |
| 2 | Qwen 3 14B | 90.68 | #1284 |
| 3 | Qwen 3 32B | 88.98 | #983 |
| 4 | Qwen 3 235B A22B | 88.98 | #633 |
| 5 | Qwen 3 8B | 87.29 | #1890 |
| 6 | Gemini 2.5 Flash | 83.9 | #466 |
| 7 | Claude Haiku 4.5 | 83.9 | #587 |
| 8 | DeepSeek V3.1 | 83.05 | #511 |
| 9 | Qwen 3 30B A3B | 82.2 | #1165 |
| 10 | Gemma 3 27B (IT) | 66.95 | #1341 |
| 11 | Llama 3.3 70B Instruct | 35.59 | #1394 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=math-pt-pt-br-mc-level-2 · How It Works · Data refreshed daily, snapshot 2026-11-22.