Llama 3 8B Dolfin V0.2 Instruct: benchmark results
Provider: Meta.
Aggregate Rating 1413 ± 34, rank #5501 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 66.37 | Accuracy (%) (5-shot) | 87.1 |
| Open LLM Leaderboard v1 - GSM8K | 56.94 | Accuracy (%) (5-shot) | 68.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.86 | Normalized accuracy (%) (25-shot) | 54.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.32 | MC2 (%) (0-shot) | 51.6 |
| Open LLM Leaderboard v1 - WinoGrande | 74.74 | Accuracy (%) (5-shot) | 38.5 |
| Open LLM Leaderboard v1 - HellaSwag | 77.86 | Normalized accuracy (%) (10-shot) | 32.1 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-dolfin-v0-2-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.