llama-m: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1301 ± 17, rank #2456 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 25.76 | Normalized accuracy (%) | 81.3 |
| Open Korean LLM - KorNAT-Harmless | 62.02 | Normalized accuracy (%) | 37.1 |
| Open Korean LLM - KorNAT-Helpful | 44.35 | Normalized accuracy (%) | 29.1 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 19.06 | Strict accuracy, prompt/instruction mean (%) | 15.1 |
| Open Korean LLM Leaderboard | 28.53 | Average Score (%) | 6.8 |
| Open Ko-LLM Leaderboard | 28.53 | Average (%) | 6.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0.15 | Exact match, flexible extract (%) | 6.3 |
| Open Korean LLM - Ko-Winogrande | 49.01 | Accuracy (%) | 1.1 |
| Open Korean LLM - KorNAT-CKA | 5.58 | Normalized accuracy (%) | 0.1 |
Interactive version: theaggregate.ai/model?slug=llama-m · How It Works · Data refreshed daily, snapshot 2026-09-19.