Logical-CommonsenseQA (3-Shot) - Mixed: leaderboard

Metric: Macro-F1 (%; operators mixed across the four options of a question; three labelled examples in the prompt; 250 human-validated four-option test questions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.

Top models

#ModelScore
1Qwen 2.5 7B Instruct51.4
2Llama 3.3 70B Instruct50.4
3Llama 3.1 8B Instruct42.8

Interactive version: theaggregate.ai/benchmark?slug=logical-commonsenseqa-3-shot-mixed · How It Works · Data refreshed daily, snapshot 2026-09-26.