T3Q-ko-gemma2-9B-it-safe-v1: benchmark results
Provider: Other. Released 2024-11-03. Access: Open.
Unified ELO 1593 ± 17, rank #651 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-IFEval | 68.42 | Strict accuracy, prompt/instruction mean (%) | 99.6 |
| Open Korean LLM - Ko-EQ-Bench | 60.21 | EQ-Bench score | 99.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 69.6 | Exact match, flexible extract (%) | 98.2 |
| Open Ko-LLM Leaderboard | 51.72 | Average (%) | 98.1 |
| Open Korean LLM Leaderboard | 51.72 | Average Score (%) | 98.1 |
| Open Korean LLM - KorNAT-CKA | 33.61 | Normalized accuracy (%) | 92.7 |
| Open Korean LLM - KorNAT-Helpful | 51 | Normalized accuracy (%) | 88.5 |
| Open Korean LLM - KorNAT-Harmless | 66.93 | Normalized accuracy (%) | 87.1 |
| Open Korean LLM - Ko-Winogrande | 64.25 | Accuracy (%) | 77.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.73 | Normalized accuracy (%) | 40.9 |
Interactive version: theaggregate.ai/model?slug=t3q-ko-gemma2-9b-it-safe-v1 · How It Works · Data refreshed daily, snapshot 2026-09-19.