Qwen2-Math-72B-Instruct — benchmark results
Alibaba's 72B math-specialist fine-tune of Qwen2 for multi-step mathematical reasoning, English-only at launch. Provider: Alibaba. Released 2024-08-08. Access: Open.
Unified ELO 1574 ± 50, rank #553 of 1776 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MATH Level 5 | 55.36 | Score | 99.2 |
| Open LLM Leaderboard - GPQA | 15.77 | Score | 92.2 |
| Open LLM Leaderboard - BBH | 47.96 | Score | 87.8 |
| Open LLM Leaderboard - MuSR | 15.73 | Score | 83.7 |
| Omni-MATH | 33.68 | Overall Accuracy (%) | 78.6 |
| Open LLM Leaderboard - MMLU-Pro | 36.36 | Score | 77.5 |
| Open LLM Leaderboard - IFEval | 56.94 | Score | 68.8 |
Interactive version: theaggregate.ai/model?slug=qwen2-math-72b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.