k2s3_test_0002: benchmark results
Provider: Other. Access: Open.
Unified ELO 1346 ± 17, rank #2259 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 63.14 | Accuracy (%) | 72.6 |
| Open Korean LLM - KorNAT-Helpful | 45.12 | Normalized accuracy (%) | 34.6 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 5.38 | Exact match, flexible extract (%) | 24.6 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - KorNAT-Harmless | 60.92 | Normalized accuracy (%) | 20.7 |
| Open Korean LLM Leaderboard | 30.33 | Average Score (%) | 18.5 |
| Open Ko-LLM Leaderboard | 30.33 | Average (%) | 18.4 |
| Open Korean LLM - KorNAT-CKA | 17.33 | Normalized accuracy (%) | 14.3 |
| Open Korean LLM - Ko-IFEval | 11.98 | Strict accuracy, prompt/instruction mean (%) | 8.7 |
| Open Korean LLM - Ko-GPQA-Diamond | 19.19 | Normalized accuracy (%) | 6.4 |
Interactive version: theaggregate.ai/model?slug=k2s3-test-0002 · How It Works · Data refreshed daily, snapshot 2026-09-19.