Math-PT (pt-PT MC) - Level 4: leaderboard

Math-PT (2026) tests mathematical reasoning on problems written natively in European Portuguese; this board covers the level-4 multiple-choice questions from OPM. Accuracy in percent on the boxed answer letter, higher is better.

Metric: Accuracy (%) on the 29 level-4 multiple-choice questions in European Portuguese (OPM); 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. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-596.55#178
2Qwen 3 32B93.1#972
3Qwen 3 235B A22B93.1#628
4Qwen 3 14B82.76#1269
5Qwen 3 30B A3B82.76#1156
6Gemini 2.5 Flash79.31#463
7DeepSeek V3.179.31#511
8Claude Haiku 4.568.97#583
9Qwen 3 8B65.52#1873
10Gemma 3 27B (IT)58.62#1324
11Llama 3.3 70B Instruct24.14#1385

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=math-pt-pt-pt-mc-level-4 · How It Works · Data refreshed daily, snapshot 2026-11-21.