General-purpose evaluation of language models on Polish language tasks: sentiment, reading comprehension, question answering, cyberbullying detection, and emotional intelligence.
Comprehensive evaluation of LLMs on Polish language understanding across 29 benchmarks including sentiment analysis (PolEmo2), reading comprehension (Belebele, DYK), question answering (PolQA, PPC, PoQuAD), cyberbullying detection (CBD), KLEJ NER, PolEval 2018 Task 3, and emotional intelligence (EQ-Bench). Maintained by SpeakLeash. 5-shot evaluation.
Leading models on Open PL LLM Leaderboard.
| # | Model | poleval2018-task3 | Year | Source |
|---|---|---|---|---|
| ★ | internlm2-1_8b✓ | 60296 | 2026 | paper ↗ |
| 2 | 🚧Mistral-7B-v0.1✓ | 16142 | 2026 | paper ↗ |
| 3 | Mistral-7B-Instruct-v0.1✓ | 6910 | 2026 | paper ↗ |
| 4 | OpenChat3.5-0106-Spichlerz-Inst-001✓ | 6516 | 2026 | paper ↗ |
| 5 | 🚧polish-mistral-7B/epoch_0_hf✓ | 6352 | 2026 | paper ↗ |
| 6 | internlm2-7b✓ | 5498 | 2026 | paper ↗ |
| 7 | zephyr-7b-alpha✓ | 4464 | 2026 | paper ↗ |
| 8 | internlm2-chat-7b-sft✓ | 4270 | 2026 | paper ↗ |
| 9 | Llama-2-7b-chat-hf✓ | 4019 | 2026 | paper ↗ |
| 10 | internlm2-chat-7b✓ | 3893 | 2026 | paper ↗ |
Didn't find the model, metric, or dataset you needed? Tell us in one line. We read every message and reply within 48 hours.
Still looking for something on Polish LLM General? A missing model, a stale score, a benchmark we should cover — drop it here and we'll handle it.
Real humans read every message. We track what people are asking for and prioritize accordingly.