ku-mistral-7B-PGO-v4: benchmark results
Provider: Other. Access: Open.
Unified ELO 1378 ± 17, rank #2061 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 51.05 | Normalized accuracy (%) | 88.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.26 | Normalized accuracy (%) | 85.5 |
| Open Korean LLM - Ko-Winogrande | 60.38 | Accuracy (%) | 53.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 20.02 | Exact match, flexible extract (%) | 51.9 |
| Open Korean LLM - KorNAT-Harmless | 62.21 | Normalized accuracy (%) | 40.3 |
| Open Korean LLM Leaderboard | 31.67 | Average Score (%) | 29.1 |
| Open Ko-LLM Leaderboard | 31.67 | Average (%) | 28.9 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 17.06 | Normalized accuracy (%) | 14.2 |
| Open Korean LLM - Ko-IFEval | 0.42 | Strict accuracy, prompt/instruction mean (%) | 2.4 |
Interactive version: theaggregate.ai/model?slug=ku-mistral-7b-pgo-v4 · How It Works · Data refreshed daily, snapshot 2026-09-19.