small-instruct: benchmark results
Provider: Other. Access: Open.
Unified ELO 1353 ± 17, rank #2214 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - KorNAT-Harmless | 62.23 | Normalized accuracy (%) | 40.7 |
| Open Korean LLM - KorNAT-CKA | 21.29 | Normalized accuracy (%) | 33.8 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM Leaderboard | 30.79 | Average Score (%) | 21.7 |
| Open Ko-LLM Leaderboard | 30.79 | Average (%) | 21.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.88 | Exact match, flexible extract (%) | 20.3 |
| Open Korean LLM - Ko-IFEval | 20.99 | Strict accuracy, prompt/instruction mean (%) | 20.1 |
| Open Korean LLM - Ko-Winogrande | 54.78 | Accuracy (%) | 17.4 |
| Open Korean LLM - KorNAT-Helpful | 42.35 | Normalized accuracy (%) | 15.6 |
Interactive version: theaggregate.ai/model?slug=small-instruct · How It Works · Data refreshed daily, snapshot 2026-09-19.