Capybara-7B: benchmark results
Provider: Other.
Aggregate Rating 1319 ± 35, rank #8352 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.07 | MC2 (%) (0-shot) | 50.6 |
| Open LLM Leaderboard v1 - HellaSwag | 80.76 | Normalized accuracy (%) (10-shot) | 42.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 55.2 | Normalized accuracy (%) (25-shot) | 33 |
| Open LLM Leaderboard v1 - WinoGrande | 73.4 | Accuracy (%) (5-shot) | 31.9 |
| Open LLM Leaderboard v1 - MMLU | 48.8 | Accuracy (%) (5-shot) | 28.1 |
| Open LLM Leaderboard v1 - GSM8K | 6.9 | Accuracy (%) (5-shot) | 26.1 |
Interactive version: theaggregate.ai/model?slug=capybara-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.