KoSOLAR_merge_test_v0.1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1365 ± 18, rank #2137 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - KorNAT-Harmless | 64 | Normalized accuracy (%) | 69.2 |
| Open Korean LLM - KorNAT-Helpful | 46.3 | Normalized accuracy (%) | 44.4 |
| Open Korean LLM - Ko-IFEval | 26.36 | Strict accuracy, prompt/instruction mean (%) | 38.7 |
| Open Korean LLM Leaderboard | 31.59 | Average Score (%) | 28.3 |
| Open Ko-LLM Leaderboard | 31.59 | Average (%) | 28 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-Winogrande | 55.88 | Accuracy (%) | 22.9 |
| Open Korean LLM - KorNAT-CKA | 16 | Normalized accuracy (%) | 11.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0 | Exact match, flexible extract (%) | 2 |
Interactive version: theaggregate.ai/model?slug=kosolar-merge-test-v0-1 · How It Works · Data refreshed daily, snapshot 2026-09-19.