T3Q-LLM-sft1.0-dpo1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1550 ± 18, rank #841 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 37.65 | Normalized accuracy (%) | 97.3 |
| Open Korean LLM - Ko-EQ-Bench | 55.31 | EQ-Bench score | 96.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 27.78 | Normalized accuracy (%) | 95 |
| Open Korean LLM Leaderboard | 46.07 | Average Score (%) | 92.6 |
| Open Ko-LLM Leaderboard | 46.07 | Average (%) | 92.5 |
| Open Korean LLM - Ko-Winogrande | 68.11 | Accuracy (%) | 92.5 |
| Open Korean LLM - KorNAT-Harmless | 67.97 | Normalized accuracy (%) | 91.2 |
| Open Korean LLM - KorNAT-Helpful | 50.42 | Normalized accuracy (%) | 85.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 51.18 | Exact match, flexible extract (%) | 84.7 |
| Open Korean LLM - Ko-IFEval | 37.02 | Strict accuracy, prompt/instruction mean (%) | 77.3 |
Interactive version: theaggregate.ai/model?slug=t3q-llm-sft1-0-dpo1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.