Math-PT (pt-BR OE) - Level 3: leaderboard
Metric: Accuracy (%) on the 58 level-3 open-ended questions in Brazilian Portuguese (OBM); native-language zero-shot prompt asking for a boxed final answer, figures given as LaTeX source; Kimi K2 Thinking judges whether the final answer is mathematically equivalent to the gold answer; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 235B A22B | 93.1 |
| 2 | GPT-5 | 91.38 |
| 3 | Gemini 2.5 Flash | 91.38 |
| 4 | DeepSeek V3.1 | 86.21 |
| 5 | Qwen 3 14B | 84.48 |
| 6 | Qwen 3 32B | 82.76 |
| 7 | Qwen 3 30B A3B | 74.14 |
| 8 | Qwen 3 8B | 72.41 |
| 9 | Claude Haiku 4.5 | 70.69 |
| 10 | Gemma 3 27B (IT) | 67.24 |
| 11 | Llama 3.3 70B Instruct | 34.48 |
Interactive version: theaggregate.ai/benchmark?slug=math-pt-pt-br-oe-level-3 · How It Works · Data refreshed daily, snapshot 2026-10-07.