Marco-o1: benchmark results
Provider: Other. Access: Open.
Unified ELO 1433 ± 19, rank #1640 of 2656 rated models, from 66 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 37.46 | Score | 87.9 |
| Open Korean LLM - KorNAT-Helpful | 49.73 | Normalized accuracy (%) | 81.4 |
| Open LLM Leaderboard - MMLU-Pro | 41.17 | Score | 74.8 |
| Open Korean LLM - Ko-IFEval | 35.56 | Strict accuracy, prompt/instruction mean (%) | 73.3 |
| Open LLM Leaderboard - BBH | 53.64 | Score | 67.1 |
| Open Korean LLM - KorNAT-Harmless | 63.76 | Normalized accuracy (%) | 66.4 |
| Open Japanese LLM - Wiki NER SET F1 | 7.08 | Score (%) | 62.7 |
| Open Japanese LLM - Wiki Coreference SET F1 | 3.6 | Score (%) | 58.4 |
| Open Japanese LLM - Xlsum JA Rouge1 | 26.78 | Score (%) | 58.3 |
| Open Japanese LLM - Xlsum JA RougeLsum | 22.69 | Score (%) | 58.2 |
| Open Korean LLM - Ko-GSM8K (flexible extract) | 24.56 | Exact match, flexible extract (%) | 57.7 |
| Open Japanese LLM - Jnli Exact Match | 82.21 | Score (%) | 56.4 |
Interactive version: theaggregate.ai/model?slug=marco-o1 · How It Works · Data refreshed daily, snapshot 2026-09-19.