Nextstage: benchmark results
Provider: Other. Access: Open.
Unified ELO 1257 ± 19, rank #2567 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 45.07 | Normalized accuracy (%) | 34.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-Winogrande | 56.04 | Accuracy (%) | 24.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.43 | Exact match, flexible extract (%) | 19.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 20.2 | Normalized accuracy (%) | 13.9 |
| Open Korean LLM - KorNAT-Harmless | 60.18 | Normalized accuracy (%) | 12.2 |
| Open Korean LLM - KorNAT-CKA | 13.23 | Normalized accuracy (%) | 4.5 |
| Open Korean LLM - Ko-IFEval | 0.18 | Strict accuracy, prompt/instruction mean (%) | 1.5 |
| Open Ko-LLM Leaderboard | 26.21 | Average (%) | 1 |
| Open Korean LLM Leaderboard | 26.21 | Average Score (%) | 1 |
Interactive version: theaggregate.ai/model?slug=nextstage · How It Works · Data refreshed daily, snapshot 2026-09-19.