GeM2-Llamion-14B-LongChat: benchmark results
Provider: VAIV. Released 2024-05-29. Access: Open.
Aggregate Rating 1437 ± 38, rank #4303 of 10916 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 39.04 | EQ-Bench score | 90.1 |
| Open Korean LLM - KorNAT-CKA | 31.42 | Normalized accuracy (%) | 86.7 |
| Open Korean LLM Leaderboard | 41.64 | Average Score (%) | 83.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 32.37 | Exact match, flexible extract (%) | 66.1 |
| Open Korean LLM - Ko-Winogrande | 61.01 | Accuracy (%) | 59.2 |
| Open Chinese LLM - WinoGrande | 63.38 | Accuracy (%) | 55.6 |
| Open Chinese LLM - CMMLU | 53.51 | Accuracy (%) | 51.2 |
| Open Chinese LLM - HellaSwag | 60.08 | Accuracy (%) | 49.6 |
| Open Korean LLM - Ko-IFEval | 28.65 | Strict accuracy, prompt/instruction mean (%) | 49 |
| Open Korean LLM - KorNAT-Helpful | 45.8 | Normalized accuracy (%) | 39.5 |
| Open Chinese LLM - C-Eval Semantic | 65.04 | Accuracy (%) | 39.1 |
Interactive version: theaggregate.ai/model?slug=gem2-llamion-14b-longchat · How It Works · Data refreshed daily, snapshot 2026-11-08.