T3Q-ko-solar-sft-v2.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1438 ± 17, rank #1606 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 67.48 | Accuracy (%) | 91.3 |
| Open Korean LLM - KorNAT-Helpful | 51.28 | Normalized accuracy (%) | 89.8 |
| Open Korean LLM - KorNAT-Harmless | 65.8 | Normalized accuracy (%) | 82.5 |
| Open Korean LLM - KorNAT-CKA | 26.03 | Normalized accuracy (%) | 61.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 27.37 | Exact match, flexible extract (%) | 61.4 |
| Open Korean LLM - Ko-IFEval | 31.54 | Strict accuracy, prompt/instruction mean (%) | 60.4 |
| Open Korean LLM - Ko-EQ-Bench | 13.2 | EQ-Bench score | 58.9 |
| Open Ko-LLM Leaderboard | 35.85 | Average (%) | 54.2 |
| Open Korean LLM Leaderboard | 35.85 | Average Score (%) | 54.2 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
Interactive version: theaggregate.ai/model?slug=t3q-ko-solar-sft-v2-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.