gemma-2B-it-sum-ko: benchmark results
Provider: Google. Access: API.
Unified ELO 1332 ± 17, rank #2337 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 64.75 | Normalized accuracy (%) | 76.9 |
| Open Korean LLM - Ko-IFEval | 28.59 | Strict accuracy, prompt/instruction mean (%) | 48.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.71 | Normalized accuracy (%) | 18.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.12 | Exact match, flexible extract (%) | 18 |
| Open Korean LLM Leaderboard | 29.99 | Average Score (%) | 15.7 |
| Open Ko-LLM Leaderboard | 29.99 | Average (%) | 15.6 |
| Open Korean LLM - KorNAT-CKA | 15.18 | Normalized accuracy (%) | 8.4 |
| Open Korean LLM - Ko-Winogrande | 51.38 | Accuracy (%) | 6.4 |
| Open Korean LLM - KorNAT-Helpful | 38.62 | Normalized accuracy (%) | 3.8 |
Interactive version: theaggregate.ai/model?slug=gemma-2b-it-sum-ko · How It Works · Data refreshed daily, snapshot 2026-09-19.