GeM2-Llamion-14B-Base: benchmark results
Provider: VAIV. Released 2024-05-13. Access: Open.
Aggregate Rating 1426 ± 43, rank #4848 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 66.77 | Accuracy (%) | 89.5 |
| Open Korean LLM - KorNAT-CKA | 31.24 | Normalized accuracy (%) | 86.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Chinese LLM - HellaSwag | 64.1 | Accuracy (%) | 75.7 |
| Open Chinese LLM - CMMLU | 63.24 | Accuracy (%) | 73.7 |
| Open Chinese LLM - C-Eval Semantic | 73.4 | Accuracy (%) | 62.4 |
| Open Korean LLM - Ko-IFEval | 31.5 | Strict accuracy, prompt/instruction mean (%) | 60 |
| Open Korean LLM Leaderboard | 35.28 | Average Score (%) | 50.5 |
| Open Korean LLM - Ko-EQ-Bench | 0.37 | EQ-Bench score | 44.8 |
| Open Chinese LLM - WinoGrande | 62.51 | Accuracy (%) | 44.4 |
| Open Chinese LLM - ARC Challenge | 50.34 | Accuracy (%) | 42.6 |
| Open Chinese LLM Leaderboard | 55.74 | Official Nonzero-Task Mean (%) | 36.7 |
Interactive version: theaggregate.ai/model?slug=gem2-llamion-14b-base · How It Works · Data refreshed daily, snapshot 2026-11-08.