T3Q-ko-solar-dpo-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1458 ± 17, rank #1470 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 74.27 | Accuracy (%) | 99.4 |
| Open Korean LLM - KorNAT-Helpful | 69.88 | Normalized accuracy (%) | 99.1 |
| Open Korean LLM - KorNAT-Harmless | 79.68 | Normalized accuracy (%) | 98.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 28.28 | Normalized accuracy (%) | 96.6 |
| Open Korean LLM - KorNAT-CKA | 27.38 | Normalized accuracy (%) | 69.5 |
| Open Ko-LLM Leaderboard | 38.18 | Average (%) | 65.1 |
| Open Korean LLM Leaderboard | 38.18 | Average Score (%) | 65.1 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 18.95 | Exact match, flexible extract (%) | 50.3 |
| Open Korean LLM - Ko-EQ-Bench | 2.06 | EQ-Bench score | 48 |
| Open Korean LLM - Ko-IFEval | 26.44 | Strict accuracy, prompt/instruction mean (%) | 38.9 |
Interactive version: theaggregate.ai/model?slug=t3q-ko-solar-dpo-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.