T3Q-ko-solar-sft-dpo-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1453 ± 18, rank #1504 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 74.11 | Accuracy (%) | 99.1 |
| Open Korean LLM - KorNAT-Helpful | 66 | Normalized accuracy (%) | 98.5 |
| Open Korean LLM - KorNAT-Harmless | 76.75 | Normalized accuracy (%) | 97.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 28.28 | Normalized accuracy (%) | 96.6 |
| Open Korean LLM - KorNAT-CKA | 30.68 | Normalized accuracy (%) | 84.5 |
| Open Ko-LLM Leaderboard | 37.27 | Average (%) | 61.3 |
| Open Korean LLM Leaderboard | 37.27 | Average Score (%) | 61.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 22.74 | Exact match, flexible extract (%) | 55.4 |
| Open Korean LLM - Ko-EQ-Bench | 0.37 | EQ-Bench score | 44.7 |
| Open Korean LLM - Ko-IFEval | 25.6 | Strict accuracy, prompt/instruction mean (%) | 35.8 |
Interactive version: theaggregate.ai/model?slug=t3q-ko-solar-sft-dpo-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.