# Polish Linguistic and Cultural Competency (PLCC)

600 hand-written questions about Polish history, geography, culture and traditions, art and entertainment, grammar and vocabulary. It shows how well an AI model knows Poland and the Polish language, not just how fluent it sounds.

Category: polish. Type: leaderboard. Status: active.
Metric: Share of the 600 questions answered fully correctly (%), averaged over the six categories (higher is better).
Source: Sławomir Dadas et al. (OPI PIB) — https://huggingface.co/spaces/sdadas/plcc/resolve/main/data.json, results as of 2026-11-16, retrieved 2026-11-17, license: CC-BY-4.0.

| Rank | Model | Provider | Overall | Art & entertainment | Culture & tradition | Geography | Grammar | History | Vocabulary |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemini-4-Carbon | Google | 98.33 | 97 | 100 | 100 | 97 | 98 | 98 |
| 2 | Gemini-4-Argon | Google | 97.33 | 95 | 98 | 99 | 96 | 98 | 98 |
| 3 | Claude-Fable-5.2 | Anthropic | 97.33 | 96 | 98 | 98 | 97 | 99 | 96 |
| 4 | Gemini-3.1-Pro-Preview | Google | 97 | 95 | 100 | 100 | 93 | 98 | 96 |
| 5 | Gemini-3.8-Flash | Google | 97 | 95 | 99 | 100 | 95 | 98 | 95 |
| 6 | GPT-6.1-Sol | OpenAI | 96.83 | 93 | 98 | 98 | 98 | 99 | 95 |
| 7 | Gemini-4-Hydrogen | Google | 96.83 | 93 | 97 | 100 | 97 | 97 | 97 |
| 8 | Gemini-3.7-Flash | Google | 96.67 | 95 | 98 | 100 | 95 | 97 | 95 |
| 9 | Gemini-3.5-Flash | Google | 96.33 | 94 | 100 | 100 | 97 | 96 | 91 |
| 10 | GPT-6-Astra | OpenAI | 96.33 | 94 | 98 | 98 | 95 | 99 | 94 |
| 11 | Gemini-3.0-Pro-Preview | Google | 95.83 | 95 | 99 | 100 | 91 | 95 | 95 |
| 12 | GPT-5.5 (high reasoning) | OpenAI | 95.83 | 93 | 98 | 98 | 97 | 95 | 94 |
| 13 | Gemini-3.6-Flash | Google | 95.5 | 92 | 98 | 99 | 94 | 96 | 94 |
| 14 | Claude-Fable-5.1 | Anthropic | 95.17 | 91 | 95 | 99 | 95 | 97 | 94 |
| 15 | Claude-Fable-5 | Anthropic | 95 | 93 | 96 | 98 | 94 | 97 | 92 |
| 16 | GPT-5.6-Sol (medium reasoning) | OpenAI | 94.67 | 93 | 96 | 99 | 91 | 96 | 93 |
| 17 | GPT-5.5 (low reasoning) | OpenAI | 94.5 | 93 | 96 | 99 | 91 | 95 | 93 |
| 18 | GPT-6.1-Terra | OpenAI | 94 | 90 | 94 | 97 | 93 | 98 | 92 |
| 19 | GPT-6-Sol (medium reasoning) | OpenAI | 93.83 | 94 | 93 | 98 | 93 | 97 | 88 |
| 20 | Muse-Wonder | Meta | 93.83 | 92 | 92 | 98 | 92 | 97 | 92 |
| 21 | Claude-Opus-5.5 | Anthropic | 92.5 | 86 | 93 | 94 | 94 | 97 | 91 |
| 22 | Gemini-2.5-Pro-Preview-06-05 | Google | 92.17 | 91 | 96 | 98 | 86 | 92 | 90 |
| 23 | GPT-5.4-2026-03-05 (high reasoning) | OpenAI | 92.17 | 91 | 93 | 96 | 90 | 92 | 91 |
| 24 | Claude-Opus-5 | Anthropic | 92.17 | 86 | 94 | 97 | 92 | 96 | 88 |
| 25 | Muse-Spark-1.3 | Meta | 91.83 | 89 | 94 | 97 | 89 | 94 | 88 |

Notes: Per-category accuracies copied from the Space's data.json (253 models). The leaderboard file does not include an overall column; 'Overall' here is the plain mean of the six category scores (each category has 100 questions, so this equals the overall percentage of correct answers), and rows are ranked by it. as_of is the Space's last commit date.
