20240105_mistral-step50: benchmark results
Provider: Other. Access: Open.
Unified ELO 1454 ± 17, rank #1499 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - Ko-EQ-Bench | 27.7 | EQ-Bench score | 74.8 |
| Open Korean LLM - Ko-IFEval | 33.3 | Strict accuracy, prompt/instruction mean (%) | 65.9 |
| Open Korean LLM Leaderboard | 38.23 | Average Score (%) | 65.4 |
| Open Ko-LLM Leaderboard | 38.23 | Average (%) | 65.3 |
| Open Korean LLM - KorNAT-Helpful | 48.08 | Normalized accuracy (%) | 64.1 |
| Open Korean LLM - KorNAT-Harmless | 63.2 | Normalized accuracy (%) | 57.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 22.9 | Exact match, flexible extract (%) | 55.7 |
| Open Korean LLM - Ko-Winogrande | 57.06 | Accuracy (%) | 29.3 |
| Open Korean LLM - KorNAT-CKA | 19.12 | Normalized accuracy (%) | 22.9 |
Interactive version: theaggregate.ai/model?slug=20240105-mistral-step50 · How It Works · Data refreshed daily, snapshot 2026-09-19.