Alphallama3-8B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1333 ± 18, rank #2328 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 30.78 | Normalized accuracy (%) | 85.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - Ko-Winogrande | 57.85 | Accuracy (%) | 34.9 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.61 | Exact match, flexible extract (%) | 34.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.42 | Normalized accuracy (%) | 14.6 |
| Open Korean LLM - Ko-IFEval | 16.22 | Strict accuracy, prompt/instruction mean (%) | 11.3 |
| Open Korean LLM Leaderboard | 29.25 | Average Score (%) | 10.6 |
| Open Ko-LLM Leaderboard | 29.25 | Average (%) | 10.4 |
| Open Korean LLM - KorNAT-Helpful | 39.73 | Normalized accuracy (%) | 5.6 |
Interactive version: theaggregate.ai/model?slug=alphallama3-8b · How It Works · Data refreshed daily, snapshot 2026-09-19.