Open PL LLM - PolEmo2-OUT (generative, 5-shot): leaderboard
Sentiment classification of Polish online reviews from the out-of-domain PolEmo 2.0 test set, whose review domains are absent from training. Open PL LLM Leaderboard (SpeakLeash), 5-shot, generative variant: the answer is extracted from generated text; accuracy (%), higher is better. Runs not available on the Hugging Face Hub are excluded.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around February 2027. 318 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2 72B Instruct | 84.21 | #579 |
| 2 | Qwen 2 72B | 82.59 | #515 |
| 3 | Llama 3.3 70B Instruct | 81.78 | #541 |
| 4 | Qwen 3 32B | 81.78 | #449 |
| 5 | Llama 3.1 70B Instruct | 81.58 | #567 |
| 6 | Qwen 2.5 72B | 81.58 | #512 |
| 7 | cogito-v1-preview-qwen-14B | 81.38 | |
| 8 | Mistral Large 2 (Jul) | 81.17 | #490 |
| 9 | QwQ 32B-Preview | 80.97 | #671 |
| 10 | Llama 4 Scout Instruct | 80.57 | #547 |
| 11 | Qwen 2.5 14B Instruct | 80.36 | #654 |
| 12 | Llama 3.1 Nemotron 70B Instruct | 80.16 | #563 |
| 13 | Llama 3 70B Instruct | 79.96 | #640 |
| 14 | Qwen 2.5 32B Instruct | 79.76 | #509 |
| 15 | Mistral Large 2 (Nov) Instruct (2411) | 79.76 | #480 |
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-out-generative-5-shot · How It Works · Data refreshed daily, snapshot 2026-11-05.