Llama 2 7B Base Small Shards Samantha V1 SFT: benchmark results
Provider: Meta.
Aggregate Rating 1265 ± 17, rank #9120 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Machine Learning | 37.5 | Accuracy (%) | 71.9 |
| MMLU-by-task - Electrical Engineering | 47.59 | Accuracy (%) | 65.2 |
| MMLU-by-task - College Computer Science | 41 | Accuracy (%) | 57.6 |
| MMLU-by-task - Professional Accounting | 37.23 | Accuracy (%) | 57.6 |
| MMLU-by-task - TruthfulQA MC1 | 29.99 | Accuracy (%) | 57.4 |
| MMLU-by-task - Conceptual Physics | 40.43 | Accuracy (%) | 54.4 |
| MMLU-by-task - High School Computer Science | 46 | Accuracy (%) | 53.7 |
| MMLU-by-task - Philosophy | 54.98 | Accuracy (%) | 53.3 |
| MMLU-by-task - TruthfulQA MC2 | 45.28 | Accuracy (%) | 52.8 |
| MMLU-by-task - Abstract Algebra | 30 | Accuracy (%) | 52.2 |
| MMLU-by-task - Medical Genetics | 52 | Accuracy (%) | 52.2 |
| MMLU-by-task - College Medicine | 41.04 | Accuracy (%) | 51.1 |
Interactive version: theaggregate.ai/model?slug=llama-2-7b-base-small-shards-samantha-v1-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.