GeM2-Llamion-14B-Chat: benchmark results
Provider: VAIV. Released 2024-05-13. Access: Open.
Aggregate Rating 1433 ± 38, rank #4548 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 30.76 | Normalized accuracy (%) | 85 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - Ko-Winogrande | 63.54 | Accuracy (%) | 74.7 |
| Open Korean LLM Leaderboard | 39.42 | Average Score (%) | 72.2 |
| Open Chinese LLM - HellaSwag | 62.61 | Accuracy (%) | 68.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 32.83 | Exact match, flexible extract (%) | 66.6 |
| Open Korean LLM - Ko-EQ-Bench | 20.28 | EQ-Bench score | 66.2 |
| Open Chinese LLM - CMMLU | 57.25 | Accuracy (%) | 63.6 |
| Open Chinese LLM - C-Eval Semantic | 73.23 | Accuracy (%) | 62.1 |
| Open Korean LLM - KorNAT-Harmless | 62.97 | Normalized accuracy (%) | 52.5 |
| Open Korean LLM - KorNAT-Helpful | 46.73 | Normalized accuracy (%) | 48.5 |
| Open Chinese LLM - ARC Challenge | 51.62 | Accuracy (%) | 46.2 |
Interactive version: theaggregate.ai/model?slug=gem2-llamion-14b-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.