xllama-instruct: benchmark results
Provider: Other. Access: Open.
Unified ELO 1299 ± 18, rank #2463 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 20.06 | Normalized accuracy (%) | 27.9 |
| Open Korean LLM - KorNAT-Helpful | 43.88 | Normalized accuracy (%) | 26.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.16 | Exact match, flexible extract (%) | 24.3 |
| Open Korean LLM - Ko-Winogrande | 55.72 | Accuracy (%) | 22 |
| Open Korean LLM - KorNAT-Harmless | 60.69 | Normalized accuracy (%) | 17.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM Leaderboard | 28.1 | Average Score (%) | 4.6 |
| Open Ko-LLM Leaderboard | 28.1 | Average (%) | 4.5 |
| Open Korean LLM - Ko-IFEval | 1.35 | Strict accuracy, prompt/instruction mean (%) | 3.2 |
Interactive version: theaggregate.ai/model?slug=xllama-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.