linear-merge: benchmark results
Provider: Other. Access: Open.
Unified ELO 1393 ± 18, rank #1958 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-Winogrande | 65.11 | Accuracy (%) | 82.7 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 30.71 | Exact match, flexible extract (%) | 65.1 |
| Open Korean LLM - KorNAT-CKA | 26.38 | Normalized accuracy (%) | 64.1 |
| Open Korean LLM - KorNAT-Helpful | 47.8 | Normalized accuracy (%) | 60.8 |
| Open Korean LLM - Ko-IFEval | 31.5 | Strict accuracy, prompt/instruction mean (%) | 60.1 |
| Open Korean LLM - KorNAT-Harmless | 63.05 | Normalized accuracy (%) | 54.5 |
| Open Korean LLM - Ko-GPQA-Diamond | 22.22 | Normalized accuracy (%) | 35 |
| Open Korean LLM Leaderboard | 32.34 | Average Score (%) | 32.9 |
| Open Ko-LLM Leaderboard | 32.34 | Average (%) | 32.6 |
| Open Korean LLM - Ko-EQ-Bench | -16.19 | EQ-Bench score | 1.4 |
Interactive version: theaggregate.ai/model?slug=linear-merge · How It Works · Data refreshed daily, snapshot 2026-09-19.