AlphaMist7B-slr-v1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1449 ± 18, rank #1532 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 27.27 | Normalized accuracy (%) | 92.4 |
| Open Korean LLM - KorNAT-Harmless | 68.42 | Normalized accuracy (%) | 92 |
| Open Korean LLM - KorNAT-CKA | 33.11 | Normalized accuracy (%) | 90.5 |
| Open Korean LLM - Ko-EQ-Bench | 27.43 | EQ-Bench score | 74.5 |
| Open Korean LLM - Ko-Winogrande | 62.12 | Accuracy (%) | 66.6 |
| Open Ko-LLM Leaderboard | 36.7 | Average (%) | 58.3 |
| Open Korean LLM Leaderboard | 36.7 | Average Score (%) | 58.3 |
| Open Korean LLM - KorNAT-Helpful | 47.58 | Normalized accuracy (%) | 57.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 16.15 | Exact match, flexible extract (%) | 46.5 |
| Open Korean LLM - Ko-IFEval | 23.83 | Strict accuracy, prompt/instruction mean (%) | 28.7 |
Interactive version: theaggregate.ai/model?slug=alphamist7b-slr-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.