Llama 2 7B Base Small Shards Samantha V1 SFT [4bit]: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1291 ± 36, rank #8855 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 73.8 | Accuracy (%) (5-shot) | 33.6 |
| Open LLM Leaderboard v1 - HellaSwag | 77.71 | Normalized accuracy (%) (10-shot) | 31.6 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 45.28 | MC2 (%) (0-shot) | 30.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 53.16 | Normalized accuracy (%) (25-shot) | 28.8 |
| Open LLM Leaderboard v1 - GSM8K | 6.37 | Accuracy (%) (5-shot) | 25.5 |
| Open LLM Leaderboard v1 - MMLU | 43.47 | Accuracy (%) (5-shot) | 22.6 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-base-small-shards-samantha-v1-sft-4bit · How It Works · Data refreshed daily, snapshot 2026-11-08.