CausalLM-Platypus-14B: benchmark results
Provider: KnutJaegersberg. Access: Open.
Aggregate Rating 1401 ± 35, rank #6065 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 64.98 | Accuracy (%) (5-shot) | 79.7 |
| Open LLM Leaderboard v1 - GSM8K | 57.24 | Accuracy (%) (5-shot) | 69.1 |
| Open LLM Leaderboard v1 - WinoGrande | 76.01 | Accuracy (%) (5-shot) | 45.4 |
| Open LLM Leaderboard v1 - HellaSwag | 80.06 | Normalized accuracy (%) (10-shot) | 39.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 47.57 | MC2 (%) (0-shot) | 38.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 56.91 | Normalized accuracy (%) (25-shot) | 36.3 |
Interactive version: theaggregate.ai/model?slug=causallm-platypus-14b · How It Works · Data refreshed daily, snapshot 2026-11-08.