Dolphin-Llama-13B: benchmark results
Provider: Cognitive Computations. Access: Open.
Aggregate Rating 1319 ± 14, rank #8357 of 10916 rated models, from 69 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC1 | 37.45 | Accuracy (%) | 90.6 |
| MMLU-by-task - TruthfulQA MC2 | 52.23 | Accuracy (%) | 86.2 |
| MMLU-by-task - Management | 75.73 | Accuracy (%) | 84.7 |
| MMLU-by-task - Elementary Mathematics | 35.45 | Accuracy (%) | 84.2 |
| MMLU-by-task - Security Studies | 64.9 | Accuracy (%) | 82.5 |
| MMLU-by-task - Conceptual Physics | 46.81 | Accuracy (%) | 80.9 |
| MMLU-by-task - International Law | 73.55 | Accuracy (%) | 78.8 |
| MMLU-by-task - Moral Scenarios | 37.65 | Accuracy (%) | 77.5 |
| MMLU-by-task - Abstract Algebra | 33 | Accuracy (%) | 75.6 |
| MMLU-by-task - Nutrition | 60.46 | Accuracy (%) | 74.9 |
| MMLU-by-task - Sociology | 72.64 | Accuracy (%) | 73.7 |
| MMLU-by-task - Econometrics | 31.58 | Accuracy (%) | 73.2 |
Interactive version: theaggregate.ai/model?slug=dolphin-llama-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.