T3Q-ko-solar-dpo-v7.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1514 ± 18, rank #1014 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 50.77 | Normalized accuracy (%) | 100 |
| Open Korean LLM - KorNAT-Helpful | 82.2 | Normalized accuracy (%) | 100 |
| Open Korean LLM - Ko-Winogrande | 76.09 | Accuracy (%) | 99.8 |
| Open Korean LLM - KorNAT-Harmless | 86.63 | Normalized accuracy (%) | 99.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 28.79 | Normalized accuracy (%) | 98.1 |
| Open Korean LLM Leaderboard | 43.29 | Average Score (%) | 87.6 |
| Open Ko-LLM Leaderboard | 43.29 | Average (%) | 87.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 10.24 | Exact match, flexible extract (%) | 34 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 19.68 | Strict accuracy, prompt/instruction mean (%) | 16.9 |
Interactive version: theaggregate.ai/model?slug=t3q-ko-solar-dpo-v7-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.