Llama 3 8B Instruct Dolfin V0.1 [bfloat16] [rev: 2440cf34ccb5]: benchmark results
Provider: Meta.
Aggregate Rating 1413 ± 34, rank #5508 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 65.69 | Accuracy (%) (5-shot) | 85.2 |
| Open LLM Leaderboard v1 - GSM8K | 62.17 | Accuracy (%) (5-shot) | 75.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.52 | Normalized accuracy (%) (25-shot) | 53.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.76 | MC2 (%) (0-shot) | 53.2 |
| Open LLM Leaderboard v1 - WinoGrande | 75.53 | Accuracy (%) (5-shot) | 42.7 |
| Open LLM Leaderboard v1 - HellaSwag | 79.25 | Normalized accuracy (%) (10-shot) | 37.2 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-instruct-dolfin-v0-1-bfloat16-rev-2440cf34ccb5 · How It Works · Data refreshed daily, snapshot 2026-11-08.