algograpV4: benchmark results
Provider: Other. Access: Open.
Unified ELO 1537 ± 17, rank #906 of 2656 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-EQ-Bench | 52.05 | EQ-Bench score | 95.9 |
| Open Korean LLM - Ko-Winogrande | 69.93 | Accuracy (%) | 95.9 |
| Open Korean LLM Leaderboard | 45.43 | Average Score (%) | 91.9 |
| Open Ko-LLM Leaderboard | 45.43 | Average (%) | 91.8 |
| Open Korean LLM - KorNAT-CKA | 33.01 | Normalized accuracy (%) | 90.1 |
| Open Korean LLM - KorNAT-Harmless | 66.03 | Normalized accuracy (%) | 83.9 |
| Open Korean LLM - Ko-IFEval | 36.87 | Strict accuracy, prompt/instruction mean (%) | 76.8 |
| Open Korean LLM - Ko-GPQA-Diamond | 24.75 | Normalized accuracy (%) | 69.5 |
| Open Korean LLM - KorNAT-Helpful | 48.25 | Normalized accuracy (%) | 66.3 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 29.49 | Exact match, flexible extract (%) | 63.9 |
Interactive version: theaggregate.ai/model?slug=algograpv4 · How It Works · Data refreshed daily, snapshot 2026-09-19.