Platypus2-70B-Instruct-GPTQ: benchmark results
Provider: Other.
Aggregate Rating 1430 ± 21, rank #4639 of 10916 rated models, from 62 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MMLU-by-task - ARC Challenge | 69.2 | Accuracy (%) | 99.9 |
| MMLU-by-task - High School European History | 87.88 | Accuracy (%) | 99.9 |
| MMLU-by-task - High School Psychology | 90.83 | Accuracy (%) | 99.9 |
| MMLU-by-task - Formal Logic | 53.97 | Accuracy (%) | 99.7 |
| MMLU-by-task - College Mathematics | 44 | Accuracy (%) | 99.5 |
| MMLU-by-task - High School Government And Politics | 94.82 | Accuracy (%) | 99.5 |
| MMLU-by-task - Management | 84.47 | Accuracy (%) | 99.5 |
| MMLU-by-task - Moral Scenarios | 64.69 | Accuracy (%) | 99.5 |
| MMLU-by-task - Professional Law | 58.6 | Accuracy (%) | 99.4 |
| MMLU-by-task - Clinical Knowledge | 74.72 | Accuracy (%) | 99.2 |
| MMLU-by-task - High School Microeconomics | 78.15 | Accuracy (%) | 99 |
| MMLU-by-task - Logical Fallacies | 82.82 | Accuracy (%) | 99 |
Interactive version: theaggregate.ai/model?slug=platypus2-70b-instruct-gptq · How It Works · Data refreshed daily, snapshot 2026-11-08.