Math-PT (pt-PT MC) - Level 2: leaderboard

Math-PT (2026) tests mathematical reasoning on problems written natively in European Portuguese; this board covers the level-2 multiple-choice questions from OPM. Accuracy in percent on the boxed answer letter, higher is better.

Metric: Accuracy (%) on the 169 level-2 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: Around February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-594.67#178
2Qwen 3 14B89.35#1269
3Qwen 3 235B A22B86.98#628
4DeepSeek V3.184.02#511
5Qwen 3 32B83.43#972
6Qwen 3 30B A3B82.84#1156
7Qwen 3 8B76.33#1873
8Gemini 2.5 Flash75.74#463
9Claude Haiku 4.574.56#583
10Gemma 3 27B (IT)49.11#1324
11Llama 3.3 70B Instruct32.54#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-2 · How It Works · Data refreshed daily, snapshot 2026-11-21.