Math-PT (pt-PT OE) - Level 1: leaderboard
Math-PT (2026) tests mathematical reasoning on problems written natively in European Portuguese; this board covers the level-1 open-ended questions from OPM. Accuracy in percent, with Kimi K2 Thinking checking that the final answer is mathematically equivalent to the gold answer, higher is better.
Metric: Accuracy (%) on the 34 level-1 open-ended questions in European Portuguese (OPM); 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. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 100 | #185 |
| 2 | Gemini 2.5 Flash | 88.24 | #466 |
| 3 | Qwen 3 235B A22B | 88.24 | #633 |
| 4 | Qwen 3 8B | 82.35 | #1890 |
| 5 | Qwen 3 14B | 82.35 | #1284 |
| 6 | Qwen 3 30B A3B | 82.35 | #1165 |
| 7 | Qwen 3 32B | 79.41 | #983 |
| 8 | DeepSeek V3.1 | 73.53 | #511 |
| 9 | Claude Haiku 4.5 | 67.65 | #587 |
| 10 | Gemma 3 27B (IT) | 58.82 | #1341 |
| 11 | Llama 3.3 70B Instruct | 38.24 | #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-pt-oe-level-1 · How It Works · Data refreshed daily, snapshot 2026-11-22.