AULM-12.8B-v0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1351 ± 18, rank #2228 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-IFEval | 23.57 | Strict accuracy, prompt/instruction mean (%) | 27.5 |
| Open Korean LLM - KorNAT-CKA | 19.67 | Normalized accuracy (%) | 26 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 61.08 | Normalized accuracy (%) | 22.5 |
| Open Korean LLM Leaderboard | 30.81 | Average Score (%) | 21.8 |
| Open Ko-LLM Leaderboard | 30.81 | Average (%) | 21.7 |
| Open Korean LLM - Ko-Winogrande | 55.49 | Accuracy (%) | 20.7 |
| Open Korean LLM - KorNAT-Helpful | 41.7 | Normalized accuracy (%) | 13.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.23 | Exact match, flexible extract (%) | 7.3 |
Interactive version: theaggregate.ai/model?slug=aulm-12-8b-v0 · How It Works · Data refreshed daily, snapshot 2026-09-19.