Logical-CommonsenseQA (3-Shot) - NEITHER/NOR: leaderboard

Metric: Macro-F1 (%; neither composed statement may be plausible; three labelled examples in the prompt; 250 human-validated four-option test questions). Source: arxiv.org. Saturation forecast: Around February 2028. 3 models tracked.

Top models

#ModelScore
1Llama 3.3 70B Instruct10.7
2Qwen 2.5 7B Instruct6.8
3Llama 3.1 8B Instruct6.1

Interactive version: theaggregate.ai/benchmark?slug=logical-commonsenseqa-3-shot-neither-nor · How It Works · Data refreshed daily, snapshot 2026-09-26.