AlphaMist7B-slr-v4-slow2: benchmark results
Provider: Other. Released 2024-05-10.
Aggregate Rating 1371 ± 19, rank #1332 of 1656 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 75.28 | Normalized accuracy (%) | 97.3 |
| Open Korean LLM - KorNAT-Helpful | 58.7 | Normalized accuracy (%) | 97.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 26.77 | Normalized accuracy (%) | 88.9 |
| Open Korean LLM - KorNAT-CKA | 30.73 | Normalized accuracy (%) | 84.8 |
| Open Korean LLM - Ko-Winogrande | 62.35 | Accuracy (%) | 68.1 |
| Open Korean LLM - Ko-IFEval | 29.89 | Strict accuracy, prompt/instruction mean (%) | 53.3 |
| Open Korean LLM Leaderboard | 35.28 | Average Score (%) | 51 |
| Open Ko-LLM Leaderboard | 35.28 | Average (%) | 50.8 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 15.47 | Exact match, flexible extract (%) | 45.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| LogicKor - Coding | 5.42 | Score (0-10) | 21 |
| LogicKor - Understanding | 5.64 | Score (0-10) | 20.8 |
Interactive version: theaggregate.ai/model?slug=alphamist7b-slr-v4-slow2 · How It Works · Data refreshed daily, snapshot 2026-10-20.