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

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MATH Level 555.36Score99.2
Open LLM Leaderboard - GPQA15.77Score92.2
Open LLM Leaderboard - BBH47.96Score87.8
Open LLM Leaderboard - MuSR15.73Score83.7
Omni-MATH33.68Overall Accuracy (%)78.6
Open LLM Leaderboard - MMLU-Pro36.36Score77.5
Open LLM Leaderboard - IFEval56.94Score68.8

Interactive version: theaggregate.ai/model?slug=qwen2-math-72b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.