T3Q-LLM1-sft1.0-dpo1.0: benchmark results
Provider: Other. Released 2024-05-27. Access: Open.
Unified ELO 1563 ± 19, rank #783 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 31.31 | Normalized accuracy (%) | 99.9 |
| Open Korean LLM - KorNAT-Harmless | 74.24 | Normalized accuracy (%) | 97 |
| Open Korean LLM - KorNAT-Helpful | 56.75 | Normalized accuracy (%) | 96.5 |
| Open Korean LLM - KorNAT-CKA | 34.72 | Normalized accuracy (%) | 94.4 |
| Open Korean LLM - Ko-EQ-Bench | 44.67 | EQ-Bench score | 93.8 |
| Open Korean LLM Leaderboard | 46.4 | Average Score (%) | 93.3 |
| Open Ko-LLM Leaderboard | 46.4 | Average (%) | 93.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 58.91 | Exact match, flexible extract (%) | 93 |
| Open Korean LLM - Ko-Winogrande | 68.27 | Accuracy (%) | 92.8 |
| Open Korean LLM - Ko-IFEval | 44.45 | Strict accuracy, prompt/instruction mean (%) | 88.9 |
Interactive version: theaggregate.ai/model?slug=t3q-llm1-sft1-0-dpo1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.