Llama-3-Base-8B-SFT-RRHF: benchmark results
Provider: Meta. Released 2024-07-06. Access: Open.
Unified ELO 1443 ± 1, rank #1088 of 1553 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 39.02 | Average Score (%) | 66.7 |
| Open LLM Leaderboard - GPQA | 7.38 | Score | 62.2 |
| Open LLM Leaderboard - BBH | 23.66 | Score | 35.8 |
| Open LLM Leaderboard - MuSR | 7.56 | Score | 35.2 |
| Open LLM Leaderboard - MMLU-Pro | 20.99 | Score | 33.1 |
| Open LLM Leaderboard - IFEval | 33.57 | Score | 31.6 |
| Open LLM Leaderboard - MATH Level 5 | 4.53 | Score | 25.7 |
Interactive version: theaggregate.ai/model?slug=llama-3-base-8b-sft-rrhf · How It Works · Data refreshed daily, snapshot 2026-09-08.