240104_mistral_lora: benchmark results
Provider: Other. Access: Open.
Unified ELO 1430 ± 17, rank #1668 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 49.33 | Normalized accuracy (%) | 78.5 |
| Open Korean LLM - Ko-EQ-Bench | 17.71 | EQ-Bench score | 63.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - Ko-IFEval | 30.27 | Strict accuracy, prompt/instruction mean (%) | 55.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 22.37 | Exact match, flexible extract (%) | 54.9 |
| Open Korean LLM Leaderboard | 35.92 | Average Score (%) | 54.7 |
| Open Ko-LLM Leaderboard | 35.92 | Average (%) | 54.6 |
| Open Korean LLM - KorNAT-Harmless | 62.19 | Normalized accuracy (%) | 39.9 |
| Open Korean LLM - Ko-Winogrande | 57.06 | Accuracy (%) | 29.3 |
| Open Korean LLM - KorNAT-CKA | 18.38 | Normalized accuracy (%) | 19.4 |
Interactive version: theaggregate.ai/model?slug=240104-mistral-lora · How It Works · Data refreshed daily, snapshot 2026-09-19.