Llama 2 7B Chat Instruct Pl Lora Unload: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1301 ± 34, rank #8723 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - HellaSwag | 77.49 | Normalized accuracy (%) (10-shot) | 31 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.99 | Normalized accuracy (%) (25-shot) | 28.3 |
| Open LLM Leaderboard v1 - WinoGrande | 72.06 | Accuracy (%) (5-shot) | 28.1 |
| Open LLM Leaderboard v1 - GSM8K | 6.9 | Accuracy (%) (5-shot) | 26.1 |
| Open LLM Leaderboard v1 - MMLU | 47.12 | Accuracy (%) (5-shot) | 26 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.61 | MC2 (%) (0-shot) | 21.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-chat-instruct-pl-lora-unload · How It Works · Data refreshed daily, snapshot 2026-11-08.