Math-PT (pt-PT MC) - Level 3: leaderboard

Math-PT (2026) tests mathematical reasoning on problems written natively in European Portuguese; this board covers the level-3 multiple-choice questions from OPM. Accuracy in percent on the boxed answer letter, higher is better.

Metric: Accuracy (%) on the 143 level-3 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-596.5#185
2DeepSeek V3.188.81#511
3Qwen 3 235B A22B88.11#633
4Qwen 3 14B86.71#1284
5Qwen 3 30B A3B86.71#1165
6Qwen 3 32B85.31#983
7Gemini 2.5 Flash83.92#466
8Qwen 3 8B78.32#1890
9Claude Haiku 4.576.92#587
10Gemma 3 27B (IT)48.95#1341
11Llama 3.3 70B Instruct23.78#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-mc-level-3 · How It Works · Data refreshed daily, snapshot 2026-11-22.