AlphaMist7B-slr-v3: benchmark results
Provider: Other. Access: Open.
Unified ELO 1440 ± 17, rank #1590 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 35.04 | Normalized accuracy (%) | 95.2 |
| Open Korean LLM - KorNAT-Harmless | 69.97 | Normalized accuracy (%) | 93.1 |
| Open Korean LLM - KorNAT-Helpful | 50.88 | Normalized accuracy (%) | 87.8 |
| Open Korean LLM - Ko-Winogrande | 63.93 | Accuracy (%) | 76.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.24 | Normalized accuracy (%) | 62.4 |
| Open Korean LLM - Ko-EQ-Bench | 16.58 | EQ-Bench score | 62.1 |
| Open Korean LLM Leaderboard | 35.88 | Average Score (%) | 54.5 |
| Open Ko-LLM Leaderboard | 35.88 | Average (%) | 54.4 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 18.12 | Exact match, flexible extract (%) | 49.4 |
| Open Korean LLM - Ko-IFEval | 22.61 | Strict accuracy, prompt/instruction mean (%) | 24 |
Interactive version: theaggregate.ai/model?slug=alphamist7b-slr-v3 · How It Works · Data refreshed daily, snapshot 2026-09-19.