gemma-ko-7B-instruct-v0.52: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1325 ± 29, rank #8249 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 36.43 | Normalized accuracy (%) | 96.6 |
| Open Korean LLM - Ko-Winogrande | 65.35 | Accuracy (%) | 84 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM Leaderboard | 37.59 | Average Score (%) | 62.9 |
| Open Korean LLM - Ko-EQ-Bench | 15.97 | EQ-Bench score | 61.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 15.39 | Exact match, flexible extract (%) | 44.9 |
| Open Korean LLM - Ko-IFEval | 25.41 | Strict accuracy, prompt/instruction mean (%) | 35.1 |
| Open LLM Leaderboard v1 - GSM8K | 11.98 | Accuracy (%) (5-shot) | 33.5 |
| Open LLM Leaderboard v1 - MMLU | 49.57 | Accuracy (%) (5-shot) | 28.8 |
| Open Korean LLM - KorNAT-Helpful | 44.3 | Normalized accuracy (%) | 28.5 |
| Open LLM Leaderboard v1 - WinoGrande | 71.82 | Accuracy (%) (5-shot) | 27.4 |
| Open LLM Leaderboard v1 - HellaSwag | 75.54 | Normalized accuracy (%) (10-shot) | 26.7 |
Interactive version: theaggregate.ai/model?slug=gemma-ko-7b-instruct-v0-52 · How It Works · Data refreshed daily, snapshot 2026-11-08.