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

#ModelScoreOverall rank
1GPT-5100#185
2Gemini 2.5 Flash88.24#466
3Qwen 3 235B A22B88.24#633
4Qwen 3 8B82.35#1890
5Qwen 3 14B82.35#1284
6Qwen 3 30B A3B82.35#1165
7Qwen 3 32B79.41#983
8DeepSeek V3.173.53#511
9Claude Haiku 4.567.65#587
10Gemma 3 27B (IT)58.82#1341
11Llama 3.3 70B Instruct38.24#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.