Llama3 — benchmark results
A Meta Llama 3 model row (April 2024 family, released as 8B and 70B base/instruct under the Llama 3 Community License); board label does not specify size or variant. Provider: Meta. Released 2024-04-18. Access: Open.
Unified ELO 1414 ± 45, rank #1163 of 1776 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Fibble2 Arena | 3.03 | Win Rate (%) | 88.9 |
| Open LLM Leaderboard - GPQA | 8.05 | Score | 67.9 |
| Fibble Arena | 6.25 | Win Rate (%) | 54.3 |
| RULER | 86.5 | Avg Accuracy (%) | 52.5 |
| Open LLM Leaderboard - MMLU-Pro | 24.02 | Score | 42.6 |
| Open LLM Leaderboard - BBH | 26.71 | Score | 42 |
| Fibble4 Arena | 0 | Win Rate (%) | 40.5 |
| Fibble3 Arena | 0 | Win Rate (%) | 39.3 |
| Fibble5 Arena | 0 | Win Rate (%) | 36.7 |
| Wordle Arena | 3.12 | Win Rate (%) | 34.4 |
| Open LLM Leaderboard - MuSR | 7.1 | Score | 33.4 |
| Open LLM Leaderboard - MATH Level 5 | 5.66 | Score | 31.3 |
Interactive version: theaggregate.ai/model?slug=llama3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.