Llama 2 13B FINETUNE2.3w: benchmark results
Provider: Meta. Access: Open.
Aggregate Rating 1338 ± 18, rank #8006 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - Abstract Algebra | 39 | Accuracy (%) | 98 |
| MMLU-by-task - High School Mathematics | 32.22 | Accuracy (%) | 89.1 |
| MMLU-by-task - Miscellaneous | 77.65 | Accuracy (%) | 86.4 |
| MMLU-by-task - Computer Security | 71 | Accuracy (%) | 86.2 |
| MMLU-by-task - Clinical Knowledge | 61.89 | Accuracy (%) | 85.3 |
| MMLU-by-task - Prehistory | 66.05 | Accuracy (%) | 84.1 |
| MMLU-by-task - College Computer Science | 48 | Accuracy (%) | 83.8 |
| MMLU-by-task - Astronomy | 57.24 | Accuracy (%) | 79.7 |
| MMLU-by-task - Management | 73.79 | Accuracy (%) | 79.4 |
| MMLU-by-task - High School Computer Science | 58 | Accuracy (%) | 78.9 |
| MMLU-by-task - Marketing | 81.2 | Accuracy (%) | 78.8 |
| MMLU-by-task - Electrical Engineering | 50.34 | Accuracy (%) | 77 |
Interactive version: theaggregate.ai/model?slug=llama-2-13b-finetune2-3w · How It Works · Data refreshed daily, snapshot 2026-11-08.