mistral-7B-wiki: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1364 ± 17, rank #2145 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 14.78 | Exact match, flexible extract (%) | 43.6 |
| Open Korean LLM - Ko-Winogrande | 58.88 | Accuracy (%) | 42.2 |
| Open Korean LLM - Ko-IFEval | 24.46 | Strict accuracy, prompt/instruction mean (%) | 30.2 |
| Open Korean LLM Leaderboard | 31.12 | Average Score (%) | 25.3 |
| Open Ko-LLM Leaderboard | 31.12 | Average (%) | 25.2 |
| Open Korean LLM - KorNAT-Helpful | 43.6 | Normalized accuracy (%) | 24.3 |
| Open Korean LLM - KorNAT-Harmless | 60.87 | Normalized accuracy (%) | 20 |
| Open Korean LLM - KorNAT-CKA | 18.18 | Normalized accuracy (%) | 18.2 |
| Open Korean LLM - Ko-EQ-Bench | -0.18 | EQ-Bench score | 5.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 17.68 | Normalized accuracy (%) | 1.3 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-wiki · How It Works · Data refreshed daily, snapshot 2026-09-19.