familidata-gemma7B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1375 ± 17, rank #2090 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 64.43 | Normalized accuracy (%) | 74.3 |
| Open Korean LLM - KorNAT-CKA | 26.85 | Normalized accuracy (%) | 66.9 |
| Open Korean LLM - Ko-IFEval | 33.38 | Strict accuracy, prompt/instruction mean (%) | 66.3 |
| Open Korean LLM - Ko-EQ-Bench | 0.33 | EQ-Bench score | 44.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM Leaderboard | 32.01 | Average Score (%) | 30.6 |
| Open Ko-LLM Leaderboard | 32.01 | Average (%) | 30.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.84 | Exact match, flexible extract (%) | 25.5 |
| Open Korean LLM - KorNAT-Helpful | 39.67 | Normalized accuracy (%) | 5.4 |
| Open Korean LLM - Ko-Winogrande | 50.83 | Accuracy (%) | 4.6 |
Interactive version: theaggregate.ai/model?slug=familidata-gemma7b · How It Works · Data refreshed daily, snapshot 2026-09-19.