k2s3_test_0000: benchmark results
Provider: Other. Access: Open.
Unified ELO 1353 ± 17, rank #2215 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - KorNAT-Harmless | 64.72 | Normalized accuracy (%) | 76.6 |
| Open Korean LLM - Ko-GPQA-Diamond | 23.74 | Normalized accuracy (%) | 55.6 |
| Open Korean LLM - KorNAT-CKA | 20.24 | Normalized accuracy (%) | 29.2 |
| Open Korean LLM - Ko-EQ-Bench | 0 | EQ-Bench score | 24.5 |
| Open Korean LLM - Ko-IFEval | 22.31 | Strict accuracy, prompt/instruction mean (%) | 23.2 |
| Open Ko-LLM Leaderboard | 30.88 | Average (%) | 22.4 |
| Open Korean LLM Leaderboard | 30.88 | Average Score (%) | 22.4 |
| Open Korean LLM - KorNAT-Helpful | 43.05 | Normalized accuracy (%) | 21.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 1.59 | Exact match, flexible extract (%) | 14.5 |
| Open Korean LLM - Ko-Winogrande | 53.28 | Accuracy (%) | 12 |
Interactive version: theaggregate.ai/model?slug=k2s3-test-0000 · How It Works · Data refreshed daily, snapshot 2026-09-19.