llama-3-youko-8B: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1440 ± 20, rank #1814 of 2928 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| pfgen-bench - Completion Mode - Fluency | 0.67 | Fluency Score | 66.1 |
| pfgen-bench - Completion Mode - Truthfulness | 0.81 | Truthfulness Score | 66.1 |
| pfgen-bench - Completion Mode - Score | 0.56 | pfgen Score (mean of three) | 64.5 |
| pfgen-bench - Completion Mode - Helpfulness | 0.19 | Helpfulness Score | 62.5 |
| Open LLM Leaderboard v1 - GSM8K | 34.42 | Accuracy (%) (5-shot) | 50.3 |
| Open LLM Leaderboard v1 - MMLU | 60.9 | Accuracy (%) (5-shot) | 50.1 |
| Open LLM Leaderboard v1 - HellaSwag | 79.91 | Normalized accuracy (%) (10-shot) | 39.5 |
| Open LLM Leaderboard v1 - WinoGrande | 74.59 | Accuracy (%) (5-shot) | 37.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 54.44 | Normalized accuracy (%) (25-shot) | 31.5 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.05 | MC2 (%) (0-shot) | 15.9 |
Interactive version: theaggregate.ai/model?slug=llama-3-youko-8b · How It Works · Data refreshed daily, snapshot 2026-09-23.