T3Q-ko-solar-sft-v3.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1437 ± 18, rank #1616 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GPQA-Diamond | 28.79 | Normalized accuracy (%) | 98.1 |
| Open Korean LLM - KorNAT-Helpful | 60.5 | Normalized accuracy (%) | 98 |
| Open Korean LLM - Ko-Winogrande | 70.72 | Accuracy (%) | 97.1 |
| Open Korean LLM - KorNAT-Harmless | 71.79 | Normalized accuracy (%) | 94.7 |
| Open Korean LLM - KorNAT-CKA | 29.49 | Normalized accuracy (%) | 79.8 |
| Open Korean LLM Leaderboard | 35.74 | Average Score (%) | 53.3 |
| Open Ko-LLM Leaderboard | 35.74 | Average (%) | 53.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 20.47 | Exact match, flexible extract (%) | 52.3 |
| Open Korean LLM - Ko-EQ-Bench | 0.45 | EQ-Bench score | 44.9 |
| Open Korean LLM - Ko-IFEval | 25.62 | Strict accuracy, prompt/instruction mean (%) | 36 |
Interactive version: theaggregate.ai/model?slug=t3q-ko-solar-sft-v3-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.