Mistral_sum_test01: benchmark results
Provider: Mistral. Access: Open.
Unified ELO 1229 ± 22, rank #2600 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 62.07 | Normalized accuracy (%) | 37.5 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 2.12 | Exact match, flexible extract (%) | 18 |
| Open Korean LLM - Ko-Winogrande | 53.04 | Accuracy (%) | 11.5 |
| Open Korean LLM - KorNAT-Helpful | 41.15 | Normalized accuracy (%) | 10.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.7 | Normalized accuracy (%) | 9.6 |
| Open Korean LLM - Ko-IFEval | 1.65 | Strict accuracy, prompt/instruction mean (%) | 3.7 |
| Open Korean LLM - KorNAT-CKA | 12.5 | Normalized accuracy (%) | 3.5 |
| Open Ko-LLM Leaderboard | 24.85 | Average (%) | 0.2 |
| Open Korean LLM Leaderboard | 24.85 | Average Score (%) | 0.2 |
Interactive version: theaggregate.ai/model?slug=mistral-sum-test01 · How It Works · Data refreshed daily, snapshot 2026-09-19.