Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

Open LLM Leaderboard - MATH Level 5 — leaderboard

Metric: Score. Source: huggingface.co. 4576 models tracked.

Top models

#ModelScore
1Qwen 2.5 32B Instruct62.54
2Qwen2.5-Math-72B-Instruct62.39
3Awqward2.5-32B-Instruct62.31
4lambda-qwen2.5-32B-dpo-test61.03
5Qwen 2.5 72B Instruct59.82
6Qwen2.5-32B-Instruct-abliterated-v259.52
7calme-2.1-qwen2.5-72B59.14
8calme-2.2-qwen2.5-72B58.91
9zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES58.53
10Qwen2.5-Math-7B-Instruct58.08
11DeepSeek R1 Distill Qwen 14B57.02
12Qwen2.5-Math-7B-CFT55.74
13tempmotacilla-cinerea-030855.51
14Qwen2-Math-72B-Instruct55.36
15Qwen 2.5 14B Instruct55.29

Interactive version: theaggregate.ai/benchmark?slug=open-llm-leaderboard-math-level-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.