Llama 3 70B Instruct Gradient 262k [bfloat16] [rev: E77cde040bfd]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1502 ± 35, rank #2316 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 80.21 | Accuracy (%) (5-shot) | 99.7 |
| Open LLM Leaderboard v1 - MMLU | 77.11 | Accuracy (%) (5-shot) | 98.2 |
| Open LLM Leaderboard v1 - WinoGrande | 84.29 | Accuracy (%) (5-shot) | 92.8 |
| Open LLM Leaderboard v1 - HellaSwag | 86.41 | Normalized accuracy (%) (10-shot) | 80.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.66 | Normalized accuracy (%) (25-shot) | 77.7 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 54.76 | MC2 (%) (0-shot) | 63.4 |
Interactive version: theaggregate.ai/model?slug=llama-3-70b-instruct-gradient-262k-bfloat16-rev-e77cde040bfd · How It Works · Data refreshed daily, snapshot 2026-11-08.