Qwen2.5-14B-Wernicke: benchmark results
Provider: Alibaba. Released 2024-10-21. Access: Open.
Unified ELO 1657 ± 57, rank #436 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - GPQA | 39.35 | Score | 98.1 |
| Open LLM Leaderboard - MMLU-Pro | 54.24 | Score | 97.8 |
| Open Portuguese LLM - ASSIN2 RTE | 94.44 | Macro F1 (%) | 96.5 |
| Open Portuguese LLM - ENEM | 81.11 | Accuracy (%) | 94.8 |
| Open Portuguese LLM - OAB Exams | 62.19 | Accuracy (%) | 94.7 |
| Open Portuguese LLM - BLUEX | 73.3 | Accuracy (%) | 93.8 |
| Open LLM Leaderboard - BBH | 65.68 | Score | 93.5 |
| Open LLM Leaderboard - MuSR | 46.89 | Score | 91 |
| Open LLM Leaderboard - MATH Level 5 | 38.14 | Score | 88.5 |
| Open Portuguese LLM - FaQuAD NLI | 79.07 | Macro F1 (%) | 86.2 |
| Open LLM Leaderboard - IFEval | 52.35 | Score | 62.3 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-wernicke · How It Works · Data refreshed daily, snapshot 2026-09-19.