Qwen2.5-slerp-14B: benchmark results
Provider: Alibaba. Released 2024-10-17. Access: Open.
Unified ELO 1652 ± 56, rank #452 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - ASSIN2 RTE | 94.57 | Macro F1 (%) | 97.2 |
| Open LLM Leaderboard - MMLU-Pro | 53.79 | Score | 94.9 |
| Open LLM Leaderboard - MATH Level 5 | 46.22 | Score | 94.3 |
| Open Portuguese LLM - BLUEX | 73.44 | Accuracy (%) | 94.2 |
| Open Portuguese LLM - OAB Exams | 61.73 | Accuracy (%) | 94.2 |
| Open Portuguese LLM - ENEM | 80.55 | Accuracy (%) | 94 |
| Open LLM Leaderboard - MuSR | 47.44 | Score | 92.8 |
| Open LLM Leaderboard - GPQA | 36.74 | Score | 92 |
| Open LLM Leaderboard - BBH | 65.12 | Score | 91.5 |
| Open Portuguese LLM - FaQuAD NLI | 79.69 | Macro F1 (%) | 88.1 |
| Open LLM Leaderboard - IFEval | 49.28 | Score | 57.7 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-slerp-14b · How It Works · Data refreshed daily, snapshot 2026-09-19.