oxyge1-33B: benchmark results
Sakalti's TIES merge of QwQ-32B-Preview and Qwen2.5 32B Instruct built with mergekit. Provider: Sakalti. Released 2024-12-08. Access: Open.
Aggregate Rating 1528 ± 26, rank #690 of 1656 rated models, from 184 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MMLU-Pro | 59.09 | Score | 99.7 |
| Open LLM Leaderboard - BBH | 70.33 | Score | 99.1 |
| Open LLM Leaderboard - MuSR | 50.08 | Score | 98.4 |
| Open Portuguese LLM - ASSIN2 RTE | 94.69 | Macro F1 (%) | 98 |
| Open Japanese LLM - Wiki PAS SET F1 | 11.91 | Score (%) | 97.6 |
| Open Portuguese LLM - BLUEX | 78.3 | Accuracy (%) | 97.4 |
| Open Portuguese LLM - ENEM | 84.39 | Accuracy (%) | 97.4 |
| Open LLM Leaderboard - MATH Level 5 | 49.62 | Score | 96.7 |
| Open Portuguese LLM - OAB Exams | 63.33 | Accuracy (%) | 95.8 |
| Open LLM Leaderboard - GPQA | 38.26 | Score | 95.6 |
| Open Japanese LLM - Jnli Exact Match | 89.69 | Score (%) | 95.1 |
| Open Japanese LLM - Jsick Exact Match | 85.73 | Score (%) | 95 |
Interactive version: theaggregate.ai/model?slug=oxyge1-33b · How It Works · Data refreshed daily, snapshot 2026-10-20.