familidata_llama31: benchmark results
Provider: Other. Access: Open.
Unified ELO 1490 ± 17, rank #1182 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 52.99 | Exact match, flexible extract (%) | 86.7 |
| Open Korean LLM - Ko-IFEval | 42.19 | Strict accuracy, prompt/instruction mean (%) | 85.8 |
| Open Korean LLM Leaderboard | 41.43 | Average Score (%) | 82.8 |
| Open Ko-LLM Leaderboard | 41.43 | Average (%) | 82.7 |
| Open Korean LLM - Ko-EQ-Bench | 16.65 | EQ-Bench score | 62.1 |
| Open Korean LLM - KorNAT-Helpful | 47.42 | Normalized accuracy (%) | 56.7 |
| Open Korean LLM - KorNAT-CKA | 23.4 | Normalized accuracy (%) | 45 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - Ko-Winogrande | 57.62 | Accuracy (%) | 32.9 |
| Open Korean LLM - KorNAT-Harmless | 61.5 | Normalized accuracy (%) | 30 |
Interactive version: theaggregate.ai/model?slug=familidata-llama31 · How It Works · Data refreshed daily, snapshot 2026-09-19.