Logical-CommonsenseQA - Mixed: leaderboard
Metric: Macro-F1 (%; operators mixed across the four options of a question; 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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 61.8 |
| 2 | Gemini 2.5 Flash | 60.9 |
| 3 | Qwen 2.5 7B Instruct | 53.2 |
| 4 | Llama 3.3 70B Instruct | 53 |
| 5 | Llama 3.1 8B Instruct | 41.8 |
Interactive version: theaggregate.ai/benchmark?slug=logical-commonsenseqa-mixed · How It Works · Data refreshed daily, snapshot 2026-09-26.