T3Q-Llama3-8B-Inst-sft1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1472 ± 17, rank #1358 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 47.56 | Strict accuracy, prompt/instruction mean (%) | 92 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 50.49 | Exact match, flexible extract (%) | 84.1 |
| Open Korean LLM - Ko-EQ-Bench | 31.04 | EQ-Bench score | 80.1 |
| Open Korean LLM - Ko-GPQA-Diamond | 25.25 | Normalized accuracy (%) | 75.9 |
| Open Korean LLM - KorNAT-Helpful | 48.7 | Normalized accuracy (%) | 71.5 |
| Open Ko-LLM Leaderboard | 39.01 | Average (%) | 69.6 |
| Open Korean LLM Leaderboard | 39.01 | Average Score (%) | 69.6 |
| Open Korean LLM - KorNAT-CKA | 25.78 | Normalized accuracy (%) | 60.7 |
| Open Korean LLM - Ko-Winogrande | 58.48 | Accuracy (%) | 39.2 |
| Open Korean LLM - KorNAT-Harmless | 61.64 | Normalized accuracy (%) | 32.1 |
Interactive version: theaggregate.ai/model?slug=t3q-llama3-8b-inst-sft1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.