Llama 2 34B: benchmark results
Provider: Meta. Released 2023-07-18.
Aggregate Rating 1315 ± 29, rank #8451 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| TriviaQA | 84.6 | Accuracy (%) | 81.6 |
| BoolQ | 83.7 | Accuracy (%) | 64.3 |
| WinoGrande | 76.7 | Accuracy (%) | 58.8 |
| PIQA | 81.9 | Accuracy (%) | 57.5 |
| OpenBookQA | 58.2 | Accuracy (%) | 57.1 |
| ARC Challenge (AI2) | 54.5 | Accuracy (%) | 47.4 |
| GSM8K | 42.2 | Accuracy (%) | 46.2 |
| MMLU | 62.6 | Accuracy (%) | 39.9 |
| Big-Bench Hard | 44.1 | Average (%) | 37.5 |
| Epoch AI - ECI | 94.41 | ECI Score | 12 |
Interactive version: theaggregate.ai/model?slug=llama-2-34b · How It Works · Data refreshed daily, snapshot 2026-11-08.