InstructPalmyra-20B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1168 ± 16, rank #9779 of 10916 rated models, from 68 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - TruthfulQA MC1 | 27.17 | Accuracy (%) | 44.6 |
| MMLU-by-task - Global Facts | 32 | Accuracy (%) | 44.3 |
| MMLU-by-task - High School Chemistry | 31.03 | Accuracy (%) | 43.8 |
| MMLU-by-task - Elementary Mathematics | 27.25 | Accuracy (%) | 41.4 |
| MMLU-by-task - ARC Challenge | 45.56 | Accuracy (%) | 41.1 |
| MMLU-by-task - HellaSwag | 55.57 | Accuracy (%) | 40.9 |
| MMLU-by-task - Moral Scenarios | 24.69 | Accuracy (%) | 38.9 |
| MMLU-by-task - Human Aging | 40.36 | Accuracy (%) | 36.9 |
| MMLU-by-task - Philosophy | 36.66 | Accuracy (%) | 36 |
| MMLU-by-task - High School US History | 31.86 | Accuracy (%) | 35.5 |
| MMLU-by-task - TruthfulQA MC2 | 41.81 | Accuracy (%) | 35.5 |
| MMLU-by-task - High School European History | 32.12 | Accuracy (%) | 35.3 |
Interactive version: theaggregate.ai/model?slug=instructpalmyra-20b · How It Works · Data refreshed daily, snapshot 2026-11-08.