llamion-14B-base: benchmark results
Provider: Other.
Aggregate Rating 1383 ± 36, rank #6757 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 67.89 | Accuracy (%) (5-shot) | 90.1 |
| Open Korean LLM - Ko-Winogrande | 65.82 | Accuracy (%) | 86.5 |
| Open Korean LLM - KorNAT-CKA | 28.2 | Normalized accuracy (%) | 74.6 |
| Open LLM Leaderboard v1 - GSM8K | 37.98 | Accuracy (%) (5-shot) | 53.1 |
| Open Korean LLM - Ko-EQ-Bench | 0.23 | EQ-Bench score | 44.2 |
| Open Korean LLM Leaderboard | 33.57 | Average Score (%) | 42.5 |
| Open LLM Leaderboard v1 - HellaSwag | 80.57 | Normalized accuracy (%) (10-shot) | 41.4 |
| Open Korean LLM - Ko-IFEval | 26.83 | Strict accuracy, prompt/instruction mean (%) | 40.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 55.2 | Normalized accuracy (%) (25-shot) | 33 |
| Open LLM Leaderboard v1 - WinoGrande | 73.16 | Accuracy (%) (5-shot) | 31.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 7.51 | Exact match, flexible extract (%) | 29.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
Interactive version: theaggregate.ai/model?slug=llamion-14b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.