gemma_7b_hkcode20241126: benchmark results
Provider: Other. Access: Open.
Unified ELO 1384 ± 17, rank #2023 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 64.65 | Normalized accuracy (%) | 76 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - Ko-IFEval | 33.39 | Strict accuracy, prompt/instruction mean (%) | 66.6 |
| Open Korean LLM - KorNAT-CKA | 26.18 | Normalized accuracy (%) | 62.7 |
| Open Korean LLM - Ko-EQ-Bench | 2.23 | EQ-Bench score | 48.1 |
| Open Korean LLM Leaderboard | 32.52 | Average Score (%) | 34.5 |
| Open Ko-LLM Leaderboard | 32.52 | Average (%) | 34.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 4.62 | Exact match, flexible extract (%) | 23.2 |
| Open Korean LLM - Ko-Winogrande | 52.01 | Accuracy (%) | 8.2 |
| Open Korean LLM - KorNAT-Helpful | 40.25 | Normalized accuracy (%) | 7.2 |
Interactive version: theaggregate.ai/model?slug=gemma-7b-hkcode20241126 · How It Works · Data refreshed daily, snapshot 2026-09-19.