PLCC - Overall: leaderboard
PLCC (Polish Linguistic and Cultural Competency benchmark, Dadas et al. 2025): 600 open-ended questions about Polish language and culture, 100 in each of six categories. Score is the mean of the six category accuracies (0-100, higher is better), reported only for models evaluated on all six, as on the site.
Metric: Mean category accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 244 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 97.33 | #9 |
| 2 | Gemini 3.1 Pro (Preview) | 97 | #64 |
| 3 | Gemini 3.8 Flash | 97 | #30 |
| 4 | GPT-6.1 Sol | 96.83 | #7 |
| 5 | Gemini 3.7 Flash | 96.67 | #24 |
| 6 | Gemini 3.5 Flash | 96.33 | #66 |
| 7 | GPT-6 Astra | 96.33 | #6 |
| 8 | Gemini 3 Pro (Preview) | 95.83 | #71 |
| 9 | GPT-5.5 (High) | 95.83 | #33 (GPT-5.5) |
| 10 | Gemini 3.6 Flash | 95.5 | #57 |
| 11 | Claude Fable 5.1 | 95.17 | #10 |
| 12 | Claude Fable 5 | 95 | #20 |
| 13 | GPT-5.6 Sol (Medium) | 94.67 | #22 (GPT-5.6 Sol) |
| 14 | GPT-5.5 (Low) | 94.5 | #33 (GPT-5.5) |
| 15 | GPT-6.1 Terra | 94 | #15 |
Interactive version: theaggregate.ai/benchmark?slug=plcc-overall · How It Works · Data refreshed daily, snapshot 2026-11-05.