Loading data...
Villanova2-2B-Base: benchmark results
Provider: VillanovaAI. Access: Open.
Aggregate Rating 1346 ± 32, rank #7797 of 10552 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
| Lara Mini Base Report (base-model protocol) - XNLI, All Languages (0-shot) | 41 | Accuracy (%) averaged over all languages/variants of the ben | 70.4 |
| Lara Mini Base Report (base-model protocol) - ARC-Challenge (25-shot) | 55 | Accuracy normalized by answer length (%), English benchmark | 53.7 |
| Lara Mini Base Report (base-model protocol) - Belebele, All Languages (0-shot) | 33 | Accuracy (%) averaged over all languages/variants of the ben | 50 |
| Lara Mini Base Report (base-model protocol) - CRUXEval-I (2-shot) | 32.3 | pass@1, direct prediction, official answer parser (%) | 50 |
| Lara Mini Base Report (base-model protocol) - HellaSwag (10-shot) | 70.4 | Accuracy normalized by answer length (%), English benchmark | 50 |
| Lara Mini Base Report (base-model protocol) - Global PIQA (non-parallel), All Languages (0-shot) | 54.9 | Accuracy (%) averaged over all languages/variants of the ben | 46.3 |
| Lara Mini Base Report (base-model protocol) - Belebele (English) (0-shot) | 63.9 | Accuracy (%), English benchmark | 44.4 |
| Lara Mini Base Report (base-model protocol) - XNLI (English) (0-shot) | 52.9 | Accuracy (%), English benchmark | 44.4 |
| Lara Mini Base Report (base-model protocol) - INCLUDE, All Languages (5-shot) | 38 | Accuracy (%) averaged over all languages/variants of the ben | 42.6 |
| Lara Mini Base Report (base-model protocol) - T-HellaSwag, All Languages (0-shot) | 36.1 | Accuracy normalized by answer length (%) averaged over all l | 42.6 |
| Lara Mini Base Report (base-model protocol) - Global MMLU, All Languages (5-shot) | 40.2 | Accuracy (%) averaged over all languages/variants of the ben | 40.7 |
| Lara Mini Base Report (base-model protocol) - MATH (4-shot) | 26.3 | Math-Verify equivalence, Minerva prompts, 5,000 problems ove | 40.7 |
Interactive version: theaggregate.ai/model?slug=villanova2-2b-base · How It Works · Data refreshed daily, snapshot 2026-11-16.