oxyge1-33B — benchmark results
Sakalti's TIES merge of QwQ-32B-Preview and Qwen2.5 32B Instruct built with mergekit. Provider: Other. Released 2024-12-08. Access: Open.
Unified ELO 1478 ± 15, rank #881 of 1776 rated models, from 179 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MMLU-Pro | 54.55 | Score | 99.7 |
| Open LLM Leaderboard - BBH | 58.03 | Score | 99.1 |
| Open LLM Leaderboard - MuSR | 24.3 | Score | 98.9 |
| Open Japanese LLM - Wiki PAS SET F1 | 11.91 | Score (%) | 97.6 |
| Open LLM Leaderboard - MATH Level 5 | 49.62 | Score | 96.7 |
| Open LLM Leaderboard - GPQA | 17.67 | Score | 95.5 |
| Open Japanese LLM - Jnli Exact Match | 89.69 | Score (%) | 95.1 |
| Open Japanese LLM - Jsick Exact Match | 85.73 | Score (%) | 95 |
| Open Japanese LLM - MR | 94.2 | Score (%) | 94 |
| Open Japanese LLM - HE | 77.61 | Score (%) | 91.1 |
| Open Japanese LLM - NLI | 80.97 | Score (%) | 90.9 |
| Open Japanese LLM - Jmmlu Exact Match | 75.15 | Score (%) | 90.5 |
Interactive version: theaggregate.ai/model?slug=oxyge1-33b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.