T3Q-LLM-MG-v1.0: benchmark results
Provider: Other. Access: Open.
Unified ELO 1525 ± 17, rank #956 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 68.75 | Accuracy (%) | 93.9 |
| Open Korean LLM - Ko-EQ-Bench | 44.45 | EQ-Bench score | 93.6 |
| Open Korean LLM - KorNAT-Helpful | 52.33 | Normalized accuracy (%) | 92.5 |
| Open Korean LLM Leaderboard | 43.92 | Average Score (%) | 89.5 |
| Open Ko-LLM Leaderboard | 43.92 | Average (%) | 89.4 |
| Open Korean LLM - KorNAT-Harmless | 67.21 | Normalized accuracy (%) | 88.5 |
| Open Korean LLM - Ko-IFEval | 36.73 | Strict accuracy, prompt/instruction mean (%) | 76.5 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 37.91 | Exact match, flexible extract (%) | 72.3 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - KorNAT-CKA | 25.12 | Normalized accuracy (%) | 55 |
Interactive version: theaggregate.ai/model?slug=t3q-llm-mg-v1-0 · How It Works · Data refreshed daily, snapshot 2026-09-19.