llama31_common: benchmark results
Provider: Meta. Access: Open.
Unified ELO 1502 ± 17, rank #1089 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 42.64 | Strict accuracy, prompt/instruction mean (%) | 86.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 52.84 | Exact match, flexible extract (%) | 86.5 |
| Open Korean LLM Leaderboard | 42.35 | Average Score (%) | 86.2 |
| Open Ko-LLM Leaderboard | 42.35 | Average (%) | 86 |
| Open Korean LLM - Ko-EQ-Bench | 23.42 | EQ-Bench score | 68.7 |
| Open Korean LLM - KorNAT-Helpful | 47.4 | Normalized accuracy (%) | 56.3 |
| Open Korean LLM - KorNAT-CKA | 24.62 | Normalized accuracy (%) | 52.4 |
| Open Korean LLM - KorNAT-Harmless | 62.34 | Normalized accuracy (%) | 42 |
| Open Korean LLM - Ko-Winogrande | 58.48 | Accuracy (%) | 39.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 21.21 | Normalized accuracy (%) | 24 |
Interactive version: theaggregate.ai/model?slug=llama31-common · How It Works · Data refreshed daily, snapshot 2026-09-19.