Llama 2 70B Instruct V2: benchmark results
Provider: Meta.
Aggregate Rating 1435 ± 20, rank #4387 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Security Studies | 82.04 | Accuracy (%) | 99.9 |
| MMLU-by-task - HellaSwag | 69.75 | Accuracy (%) | 99.8 |
| MMLU-by-task - Astronomy | 84.21 | Accuracy (%) | 99.7 |
| MMLU-by-task - Conceptual Physics | 70.64 | Accuracy (%) | 99.6 |
| MMLU-by-task - High School US History | 92.65 | Accuracy (%) | 99.4 |
| MMLU-by-task Leaderboard | 70.58 | MMLU Average (%) | 99.4 |
| MMLU-by-task - High School Psychology | 90.28 | Accuracy (%) | 99.3 |
| MMLU-by-task - Professional Psychology | 76.47 | Accuracy (%) | 99.3 |
| MMLU-by-task - World Religions | 87.72 | Accuracy (%) | 99.3 |
| MMLU-by-task - Anatomy | 65.19 | Accuracy (%) | 99.1 |
| MMLU-by-task - High School Chemistry | 56.16 | Accuracy (%) | 99.1 |
| MMLU-by-task - High School Computer Science | 79 | Accuracy (%) | 99.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-70b-instruct-v2 · How It Works · Data refreshed daily, snapshot 2026-11-08.