openbuddy-qwen2.5llamaify-7B-v23.1-200k: benchmark results
OpenBuddy's multilingual chatbot fine-tune of Qwen2.5 7B converted to a Llama-compatible format, with a 200k context. Provider: OpenBuddy. Released 2024-10-04. Access: Open.
Aggregate Rating 1428 ± 20, rank #1115 of 1661 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM - Ko-GSM8K (flexible extract) | 55.65 | Exact match, flexible extract (%) | 89.7 |
| Open Portuguese LLM - FaQuAD NLI | 79.11 | Macro F1 (%) | 86.4 |
| Open Korean LLM - KorNAT-Harmless | 66.4 | Normalized accuracy (%) | 85.7 |
| Open Korean LLM - Ko-IFEval | 38.15 | Strict accuracy, prompt/instruction mean (%) | 79.7 |
| Open Portuguese LLM - OAB Exams | 50.34 | Accuracy (%) | 76.8 |
| Open LLM Leaderboard - MuSR | 43.63 | Score | 75.4 |
| Open Korean LLM Leaderboard | 39.8 | Average Score (%) | 74.1 |
| Open Ko-LLM Leaderboard | 39.8 | Average (%) | 74 |
| Open LLM Leaderboard - BBH | 55.09 | Score | 73.8 |
| Open Portuguese LLM - BLUEX | 58.55 | Accuracy (%) | 73.6 |
| Open LLM Leaderboard - MMLU-Pro | 39.48 | Score | 72.5 |
| Open LLM Leaderboard - GPQA | 31.46 | Score | 71.4 |
Interactive version: theaggregate.ai/model?slug=openbuddy-qwen2-5llamaify-7b-v23-1-200k · How It Works · Data refreshed daily, snapshot 2026-10-23.