Open PL LLM - PolEmo2-IN (multiple choice, 5-shot): leaderboard
Sentiment classification of Polish online reviews from the in-domain PolEmo 2.0 test set. Open PL LLM Leaderboard (SpeakLeash), 5-shot, multiple choice variant: the options are ranked by log-likelihood; accuracy (%), higher is better. Runs not available on the Hugging Face Hub are excluded.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 324 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mistral Large 2 (Jul) | 91.69 | #490 |
| 2 | Mistral Large 2 (Nov) Instruct (2411) | 89.47 | #480 |
| 3 | Bielik-11B-v2.0-Instruct | 88.78 | #750 |
| 4 | cogito-v1-preview-qwen-14B | 88.37 | |
| 5 | Llama 4 Scout Instruct | 87.95 | #547 |
| 6 | Qwen 2 72B Instruct | 87.53 | #579 |
| 7 | Qwen 2.5 72B Instruct | 87.4 | #469 |
| 8 | Bielik-11B-v2.3-Instruct | 87.4 | #700 |
| 9 | Bielik-11B-v2.2-Instruct | 87.26 | #669 |
| 10 | Qwen 2.5 14B Instruct | 87.12 | #654 |
| 11 | Bielik-11B-v2.1-Instruct | 87.12 | #679 |
| 12 | Llama 3.1 405B Instruct FP8 | 86.98 | #400 |
| 13 | Qwen 3 8B | 86.84 | #678 |
| 14 | Qwen 3 30B A3B 2507 Instruct | 86.57 | #492 |
| 15 | Phi-4 | 86.29 | #707 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-pl-llm-polemo2-in-multiple-choice-5-shot · How It Works · Data refreshed daily, snapshot 2026-11-05.