Llama 2 7B Alpaca Gpt4: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1298 ± 36, rank #8772 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 52.43 | MC2 (%) (0-shot) | 55.8 |
| Open LLM Leaderboard v1 - HellaSwag | 79.24 | Normalized accuracy (%) (10-shot) | 37.2 |
| Open LLM Leaderboard v1 - GSM8K | 9.7 | Accuracy (%) (5-shot) | 30.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.16 | Normalized accuracy (%) (25-shot) | 28.8 |
| Open LLM Leaderboard v1 - WinoGrande | 71.82 | Accuracy (%) (5-shot) | 27.4 |
| Open LLM Leaderboard v1 - MMLU | 44.15 | Accuracy (%) (5-shot) | 23.2 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-alpaca-gpt4 · How It Works · Data refreshed daily, snapshot 2026-11-08.