Mistral7B-PairRM-SPPO-Iter1: benchmark results
Provider: Mistral. Released 2024-05-04. Access: Open.
Aggregate Rating 1376 ± 37, rank #6956 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Helpful | 51.18 | Normalized accuracy (%) | 89.2 |
| Open Korean LLM - KorNAT-Harmless | 67.34 | Normalized accuracy (%) | 88.9 |
| Open Korean LLM - Ko-IFEval | 35.14 | Strict accuracy, prompt/instruction mean (%) | 72.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-EQ-Bench | 22.24 | EQ-Bench score | 67.5 |
| Open LLM Leaderboard - IFEval | 50.47 | Score | 59.8 |
| Open Korean LLM Leaderboard | 36.44 | Average Score (%) | 56.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 23.65 | Exact match, flexible extract (%) | 56.7 |
| Open LLM Leaderboard - MuSR | 39.92 | Score | 41.2 |
| Open LLM Leaderboard - GPQA | 28.36 | Score | 38.6 |
| Open LLM Leaderboard - BBH | 44.68 | Score | 33.3 |
| Open LLM Leaderboard - MMLU-Pro | 26.95 | Score | 28.5 |
Interactive version: theaggregate.ai/model?slug=mistral7b-pairrm-sppo-iter1 · How It Works · Data refreshed daily, snapshot 2026-11-08.