WinoGrande Benchmark
Explore score history ↗1,270 problems is the sample count the study audited (arXiv:2607.28801, Table 1), not the full dataset of 44k problems (arXiv:1907.10641). An adversarial Winograd Schema challenge (arXiv:1907.10641). The study notes analyses reveal persistent gender and cultural biases (arXiv:2607.28801, section 2). The annotating paper also reports full-split accuracies for Llama-3.2-1B and SmolLM-1.7B-Instruct (arXiv:2607.28801, Table 4 / App. Table 9); those rows are filed in benchmark_scores.yml.
- Released
- 2019-07-24
- Evaluates
- reasoning
- Openness
- unknown
- Importer
- Model reports
WinoGrande paper
WinoGrande results and reported scores
Reported benchmark scores · Model reports
Reported scores: 2
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite WinoGrande?
- Llama-3.2-1B and SmolLM-1.7B-Instruct Aleph Alpha Research, 2026-07-30