kosolar-4.1-sft: benchmark results
Provider: Other. Access: Open.
Unified ELO 1459 ± 17, rank #1463 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 35.16 | EQ-Bench score | 85.1 |
| Open Korean LLM - Ko-Winogrande | 65.43 | Accuracy (%) | 84.4 |
| Open Korean LLM - KorNAT-Helpful | 48.93 | Normalized accuracy (%) | 74.9 |
| Open Korean LLM - KorNAT-Harmless | 64.31 | Normalized accuracy (%) | 72.7 |
| Open Korean LLM - KorNAT-CKA | 27.06 | Normalized accuracy (%) | 67.5 |
| Open Ko-LLM Leaderboard | 38.03 | Average (%) | 64.4 |
| Open Korean LLM Leaderboard | 38.03 | Average Score (%) | 64.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 24.94 | Exact match, flexible extract (%) | 58.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
| Open Korean LLM - Ko-IFEval | 24.95 | Strict accuracy, prompt/instruction mean (%) | 31.7 |
Interactive version: theaggregate.ai/model?slug=kosolar-4-1-sft · How It Works · Data refreshed daily, snapshot 2026-09-19.