Open PL LLM - PolEmo2-IN (generative, 5-shot): leaderboard

Metric: Accuracy (%). Source: huggingface.co. 321 models tracked.

Top models

#ModelScore
1Llama 4 Scout Instruct89.34
2Qwen 2.5 14B Instruct89.06
3Mistral Large 2 (Nov) Instruct (2411)89.06
4Llama 3.1 405B Instruct FP889.06
5Mistral Large 2 (Jul)88.5
6DeepSeek V3 (0324)88.5
7Qwen 3 8B88.09
8Mistral Small 387.67
9Llama 3.1 70B Instruct87.53
10Qwen 2 72B Instruct87.26
11Llama 3.3 70B Instruct87.12
12Qwen 3 14B86.84
13Llama 3.1 Nemotron 70B Instruct86.84
14Qwen 2.5 72B Instruct86.57
15QwQ 32B-Preview86.57

Interactive version: theaggregate.ai/benchmark?slug=open-pl-llm-polemo2-in-generative-5-shot · How It Works · Data refreshed daily, snapshot 2026-09-19.