Rombos-Coder-V2.5-Qwen-32B: benchmark results
A Qwen-family base/instruct TIES merge released by rombodawg using the creator's continuous finetuning recipe. It remains distinct from the upstream Qwen releases. Provider: rombodawg. Access: Open.
Aggregate Rating 1499 ± 35, rank #2370 of 10916 rated models, from 50 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Japanese LLM - CG | 68.07 | Score (%) | 99.5 |
| Open Japanese LLM - Janli Exact Match | 87.08 | Score (%) | 90.5 |
| Open Japanese LLM - Wiki NER SET F1 | 12.39 | Score (%) | 87 |
| Open Japanese LLM - FA | 27.74 | Score (%) | 76.9 |
| Open Japanese LLM - Wiki Coreference SET F1 | 5.32 | Score (%) | 71.2 |
| Open Japanese LLM - Mbpp Pylint Check | 74.9 | Score (%) | 66.3 |
| Open Japanese LLM - Wiki Dependency SET F1 | 36.61 | Score (%) | 65.3 |
| Open Japanese LLM - Jamp Exact Match | 65.23 | Score (%) | 64.8 |
| Open Japanese LLM - MR | 89.4 | Score (%) | 63.6 |
| Open Japanese LLM - Wiki PAS SET F1 | 7.41 | Score (%) | 62.1 |
| Open Japanese LLM Leaderboard | 61.92 | Average Score (%) | 60.9 |
| Open Japanese LLM - Wiki Reading Char F1 | 76.98 | Score (%) | 53.5 |
Interactive version: theaggregate.ai/model?slug=rombos-coder-v2-5-qwen-32b · How It Works · Data refreshed daily, snapshot 2026-11-08.