LLMZSZL Leaderboard: leaderboard
Polish-language LLM leaderboard comparing open and proprietary models on Polish zero-shot and language-understanding tasks.
Metric: Score. Source: huggingface.co. Saturation forecast: Estimated already saturated. 99 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 69.06 | #454 |
| 2 | Qwen 2.5 72B | 68.5 | #499 |
| 3 | Mistral Large 2 (Jul) | 67.17 | #484 |
| 4 | Llama 3.3 70B Instruct | 67.13 | #534 |
| 5 | Qwen 3 32B | 66.84 | #443 |
| 6 | Mistral Large 2 (Nov) Instruct (2411) | 66.61 | #465 |
| 7 | Llama 3.1 70B Instruct | 66.59 | #561 |
| 8 | Llama-PLLuM-70B-chat | 64.42 | #759 |
| 9 | Llama 3 70B Instruct | 64.04 | #634 |
| 10 | Qwen 3 30B A3B | 63.52 | #493 |
| 11 | Llama 3.1 70B | 63.12 | #592 |
| 12 | Llama 3 70B | 62.22 | #631 |
| 13 | Qwen 2.5 32B | 61.04 | #546 |
| 14 | Qwen 3 14B | 61.02 | #537 |
| 15 | PLLuM-8x7B-nc-chat | 60.52 | #1067 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llmzszl-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.