Llama 3 8B Chat Base: benchmark results
Provider: Meta. Released 2024-04-18. Access: Open.
Unified ELO 1528 ± 1, rank #555 of 1392 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Jailbreak Risk | 4.21 | Risk Score | 80.2 |
| Enkrypt AI - Toxicity Risk | 1.86 | Risk Score | 71.2 |
| Enkrypt AI - Safety Risk | 22.83 | Risk Score | 67.6 |
| Enkrypt AI - Risk Score | 27.98 | Risk Score | 66.1 |
| Enkrypt AI - Insecure Code Risk | 30.22 | Risk Score | 51.3 |
| Enkrypt AI - Bias Risk | 85.27 | Risk Score | 41.5 |
| ForecastBench | 59.6 | Overall Score (higher is better) | 17.6 |
Interactive version: theaggregate.ai/model?slug=llama-3-8b-chat-base · How It Works · Data refreshed daily, snapshot 2026-09-05.