Logical-CommonsenseQA - OR: leaderboard

Metric: Macro-F1 (%; at least one composed statement must be plausible; zero-shot prompt, or the authors' fine-tunes on the training split; 250 human-validated four-option test questions). Source: arxiv.org. Saturation forecast: Around January 2028. 8 models tracked.

Top models

#ModelScore
1Gemini 2.5 Flash76.7
2Llama 3.3 70B Instruct70.9
3Gemini 3 Flash (Preview)70.1
4Qwen 2.5 7B Instruct68.9
5Llama 3.1 8B Instruct62.2

Interactive version: theaggregate.ai/benchmark?slug=logical-commonsenseqa-or · How It Works · Data refreshed daily, snapshot 2026-09-26.