Logical-CommonsenseQA - NEITHER/NOR: leaderboard

Metric: Macro-F1 (%; neither composed statement may 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 June 2028. 8 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview)39.6
2Gemini 2.5 Flash23.5
3Llama 3.3 70B Instruct13.4
4Llama 3.1 8B Instruct13.1
5Qwen 2.5 7B Instruct12.9

Interactive version: theaggregate.ai/benchmark?slug=logical-commonsenseqa-neither-nor · How It Works · Data refreshed daily, snapshot 2026-09-26.