Open PL LLM - PSC (generative, 5-shot): leaderboard
Polish Summaries Corpus: deciding whether a summary belongs to a news article. Open PL LLM Leaderboard (SpeakLeash), 5-shot, generative variant: the answer is extracted from generated text; binary F1 (%), higher is better. Runs not available on the Hugging Face Hub are excluded.
Metric: Binary F1 (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 314 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mistral Large 2 (Nov) Instruct (2411) | 99 | #480 |
| 2 | Qwen 2.5 72B Instruct | 98.99 | #469 |
| 3 | glm-4-9B | 98.94 | #865 |
| 4 | Llama 3 70B Instruct | 98.93 | #640 |
| 5 | Qwen 2.5 72B | 98.93 | #512 |
| 6 | Qwen 2 72B | 98.67 | #515 |
| 7 | c4ai-command-r-v01 | 98.59 | #993 |
| 8 | Mixtral 8x22B Instruct | 98.47 | #738 |
| 9 | Mistral Large 2 (Jul) | 98.41 | #490 |
| 10 | aya-expanse-32B | 98.39 | #687 |
| 11 | Qwen 1.5 72B | 98.35 | #752 |
| 12 | Yi 1.5 34B Chat | 98.26 | #798 |
| 13 | Qwen 1.5 32B Chat | 98.2 | #820 |
| 14 | Qwen 2 72B Instruct | 98.12 | #579 |
| 15 | Gemma 3 27B (IT) | 98.11 | #528 |
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-psc-generative-5-shot · How It Works · Data refreshed daily, snapshot 2026-11-05.