WebSquareAI-Instruct-llama-3-8B-v0.5.39: benchmark results
Provider: Other. Access: Open.
Unified ELO 1475 ± 17, rank #1341 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 33.34 | EQ-Bench score | 83.1 |
| Open Korean LLM Leaderboard | 39.87 | Average Score (%) | 74.3 |
| Open Ko-LLM Leaderboard | 39.87 | Average (%) | 74.1 |
| Open Korean LLM - Ko-IFEval | 34.87 | Strict accuracy, prompt/instruction mean (%) | 71.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 37.3 | Exact match, flexible extract (%) | 71.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - KorNAT-Helpful | 47.3 | Normalized accuracy (%) | 55.2 |
| Open Korean LLM - KorNAT-CKA | 24.27 | Normalized accuracy (%) | 50.7 |
| Open Korean LLM - Ko-Winogrande | 57.38 | Accuracy (%) | 31.3 |
| Open Korean LLM - KorNAT-Harmless | 61.29 | Normalized accuracy (%) | 26.7 |
Interactive version: theaggregate.ai/model?slug=websquareai-instruct-llama-3-8b-v0-5-39 · How It Works · Data refreshed daily, snapshot 2026-09-19.