Mistral-7B-A-u0.5-b2-ver0.4: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1350 ± 17, rank #2240 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 45.85 | Normalized accuracy (%) | 39.8 |
| Open Korean LLM - Ko-IFEval | 25.77 | Strict accuracy, prompt/instruction mean (%) | 36.6 |
| Open Korean LLM - Ko-Winogrande | 57.77 | Accuracy (%) | 34.3 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-CKA | 19.12 | Normalized accuracy (%) | 22.9 |
| Open Korean LLM Leaderboard | 30.82 | Average Score (%) | 22 |
| Open Ko-LLM Leaderboard | 30.82 | Average (%) | 21.9 |
| Open Korean LLM - KorNAT-Harmless | 60.95 | Normalized accuracy (%) | 21.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.05 | Exact match, flexible extract (%) | 17.4 |
| Open Korean LLM - Ko-GPQA-Diamond | 16.16 | Normalized accuracy (%) | 0.2 |
Interactive version: theaggregate.ai/model?slug=mistral-7b-a-u0-5-b2-ver0-4 · How It Works · Data refreshed daily, snapshot 2026-09-19.