Qwen2-7B-Multilingual-RP — benchmark results
maywell's multilingual roleplay fine-tune of Qwen2 7B with 32k context, trained on roughly 2B tokens across five languages. Provider: Alibaba. Released 2024-06-24. Access: Open.
Unified ELO 1403 ± 35, rank #1212 of 1776 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 22.43 | Score | 75.5 |
| Open Korean LLM Leaderboard | 347.66 | Average Score (%) | 70.7 |
| Open LLM Leaderboard - MMLU-Pro | 31.77 | Score | 68.7 |
| Open LLM Leaderboard - BBH | 30.54 | Score | 53.8 |
| Open LLM Leaderboard - GPQA | 6.26 | Score | 52.5 |
| Open LLM Leaderboard - IFEval | 43.47 | Score | 46 |
| Open LLM Leaderboard - MuSR | 6.23 | Score | 29.9 |
Interactive version: theaggregate.ai/model?slug=qwen2-7b-multilingual-rp · How the rankings work · Data refreshed daily, snapshot 2026-07-22.