Llama 2 13B Instructmining 40k Sharegpt: benchmark results
Provider: Meta.
Aggregate Rating 1346 ± 17, rank #7806 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - College Medicine | 58.96 | Accuracy (%) | 91.5 |
| MMLU-by-task - Abstract Algebra | 35 | Accuracy (%) | 87.4 |
| MMLU-by-task - Astronomy | 62.5 | Accuracy (%) | 87.4 |
| MMLU-by-task - Virology | 49.4 | Accuracy (%) | 87.4 |
| MMLU-by-task - TruthfulQA MC2 | 52.44 | Accuracy (%) | 86.8 |
| MMLU-by-task - College Physics | 34.31 | Accuracy (%) | 86.4 |
| MMLU-by-task - Computer Security | 71 | Accuracy (%) | 86.2 |
| MMLU-by-task - Sociology | 77.61 | Accuracy (%) | 86.1 |
| MMLU-by-task - Business Ethics | 59 | Accuracy (%) | 85.8 |
| MMLU-by-task - High School Chemistry | 45.32 | Accuracy (%) | 85.7 |
| MMLU-by-task - Human Aging | 67.26 | Accuracy (%) | 85.7 |
| MMLU-by-task - Marketing | 84.19 | Accuracy (%) | 85.7 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-instructmining-40k-sharegpt · How It Works · Data refreshed daily, snapshot 2026-11-08.