POLAR-14B_4.3_very_big_sft: benchmark results
Provider: Other. Access: Open.
Unified ELO 1439 ± 17, rank #1599 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.19 | Accuracy (%) | 83.3 |
| Open Korean LLM - KorNAT-Harmless | 65.52 | Normalized accuracy (%) | 81.1 |
| Open Korean LLM - KorNAT-CKA | 29.51 | Normalized accuracy (%) | 80 |
| Open Korean LLM - Ko-EQ-Bench | 28.83 | EQ-Bench score | 76.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 22.14 | Exact match, flexible extract (%) | 54.5 |
| Open Korean LLM Leaderboard | 35.78 | Average Score (%) | 54 |
| Open Ko-LLM Leaderboard | 35.78 | Average (%) | 53.9 |
| Open Korean LLM - KorNAT-Helpful | 46.9 | Normalized accuracy (%) | 50.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.23 | Normalized accuracy (%) | 48.1 |
| Open Korean LLM - Ko-IFEval | 21.57 | Strict accuracy, prompt/instruction mean (%) | 21.6 |
Interactive version: theaggregate.ai/model?slug=polar-14b-4-3-very-big-sft · How It Works · Data refreshed daily, snapshot 2026-09-19.