KIT-7B-v2: benchmark results
Provider: Other. Access: Open.
Unified ELO 1259 ± 18, rank #2563 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-CKA | 28.3 | Normalized accuracy (%) | 74.9 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 16.8 | Strict accuracy, prompt/instruction mean (%) | 12 |
| Open Korean LLM - KorNAT-Harmless | 59.37 | Normalized accuracy (%) | 6.1 |
| Open Korean LLM - Ko-Winogrande | 50.12 | Accuracy (%) | 3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 0 | Exact match, flexible extract (%) | 2 |
| Open Korean LLM Leaderboard | 26.9 | Average Score (%) | 1.5 |
| Open Ko-LLM Leaderboard | 26.9 | Average (%) | 1.4 |
| Open Korean LLM - KorNAT-Helpful | 35.88 | Normalized accuracy (%) | 1.4 |
Interactive version: theaggregate.ai/model?slug=kit-7b-v2 · How It Works · Data refreshed daily, snapshot 2026-09-19.