Platypus2-13B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1343 ± 28, rank #7897 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 29.9 | Strict accuracy, prompt/instruction mean (%) | 53.4 |
| Open LLM Leaderboard v1 - HellaSwag | 82.56 | Normalized accuracy (%) (10-shot) | 52.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.26 | Normalized accuracy (%) (25-shot) | 52 |
| Open LLM Leaderboard v1 - WinoGrande | 76.87 | Accuracy (%) (5-shot) | 51.3 |
| Open Korean LLM - KorNAT-Harmless | 62.84 | Normalized accuracy (%) | 50.8 |
| Open Korean LLM - Ko-Winogrande | 58.72 | Accuracy (%) | 40.8 |
| Open LLM Leaderboard v1 - MMLU | 56.7 | Accuracy (%) (5-shot) | 39.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 11.9 | Exact match, flexible extract (%) | 38 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.86 | MC2 (%) (0-shot) | 28.8 |
| Open Korean LLM Leaderboard | 31.32 | Average Score (%) | 26.8 |
| Open LLM Leaderboard v1 - GSM8K | 7.05 | Accuracy (%) (5-shot) | 26.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
Interactive version: theaggregate.ai/model?slug=platypus2-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.