Llama-3-DARE-v2-8B: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1421 ± 35, rank #5126 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 67.18 | Accuracy (%) (5-shot) | 88.9 |
| Open LLM Leaderboard v1 - GSM8K | 65.81 | Accuracy (%) (5-shot) | 80.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 62.2 | Normalized accuracy (%) (25-shot) | 56.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.77 | MC2 (%) (0-shot) | 49.5 |
| Open LLM Leaderboard v1 - WinoGrande | 75.37 | Accuracy (%) (5-shot) | 41.8 |
| Open LLM Leaderboard v1 - HellaSwag | 79.38 | Normalized accuracy (%) (10-shot) | 37.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-dare-v2-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.