LIMA2-13B-hf: benchmark results
heegyu's LIMA2 13B, Llama 2 13B fine-tuned for 10 epochs on the 64bits/lima dataset in Vicuna format. Provider: heegyu. Released 2023-08-07. Access: Open.
Aggregate Rating 1323 ± 14, rank #8275 of 10916 rated models, from 77 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - HellaSwag | 65.25 | Accuracy (%) | 89.8 |
| MMLU-by-task - High School Statistics | 47.22 | Accuracy (%) | 83.3 |
| MMLU-by-task - Astronomy | 57.24 | Accuracy (%) | 79.7 |
| MMLU-by-task - Formal Logic | 37.3 | Accuracy (%) | 79.6 |
| MMLU-by-task - High School Physics | 34.44 | Accuracy (%) | 78.7 |
| MMLU-by-task - High School Geography | 70.71 | Accuracy (%) | 77.3 |
| MMLU-by-task - Anatomy | 49.63 | Accuracy (%) | 75.9 |
| MMLU-by-task - Moral Scenarios | 36.09 | Accuracy (%) | 75.6 |
| MMLU-by-task - Public Relations | 62.73 | Accuracy (%) | 74.3 |
| MMLU-by-task - College Chemistry | 40 | Accuracy (%) | 73.8 |
| MMLU-by-task - Econometrics | 31.58 | Accuracy (%) | 73.2 |
| MMLU-by-task - Professional Medicine | 52.94 | Accuracy (%) | 73.2 |
Interactive version: theaggregate.ai/model?slug=lima2-13b-hf · How It Works · Data refreshed daily, snapshot 2026-11-08.