Qwen2.5-7B-Anvita: benchmark results
Provider: Alibaba. Access: Open.
Unified ELO 1559 ± 56, rank #803 of 2656 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Portuguese LLM - FaQuAD NLI | 80.98 | Macro F1 (%) | 91.4 |
| Open Portuguese LLM - ASSIN2 RTE | 93.34 | Macro F1 (%) | 88.8 |
| Open Portuguese LLM - ENEM | 73.62 | Accuracy (%) | 85.5 |
| Open Portuguese LLM - BLUEX | 63.7 | Accuracy (%) | 84 |
| Open LLM Leaderboard - GPQA | 32.72 | Score | 79.2 |
| Open Portuguese LLM - OAB Exams | 50.8 | Accuracy (%) | 78.4 |
| Open LLM Leaderboard - IFEval | 64.8 | Score | 76.9 |
| Open LLM Leaderboard - MMLU-Pro | 41.66 | Score | 75.8 |
| Open LLM Leaderboard - MuSR | 43.37 | Score | 73.3 |
| Open LLM Leaderboard - BBH | 54.66 | Score | 71.9 |
| Open LLM Leaderboard - MATH Level 5 | 20.17 | Score | 71.1 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-7b-anvita · How It Works · Data refreshed daily, snapshot 2026-09-19.