# Fixing Open LLM Leaderboard with Math-Verify

DevFeed: [Fixing Open LLM Leaderboard with Math-Verify](<https://devfeed.tech/articles/fixing-open-llm-leaderboard-with-math-verify-7345.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/math_verify_leaderboard>)

Author: Hynek Kydlicek; Alina Lozovskaya; Nathan Habib; Clémentine Fourrier

Published: 2025-02-14T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [math-verify](<https://devfeed.tech/topics/math-verify.md>), [open-llm-leaderboard](<https://devfeed.tech/topics/open-llm-leaderboard.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [math](<https://devfeed.tech/topics/math.md>), [Parser](<https://devfeed.tech/topics/parser.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [evals](<https://devfeed.tech/tags/evals.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [leaderboard](<https://devfeed.tech/tags/leaderboard.md>), [llm](<https://devfeed.tech/tags/llm.md>), [math-verify](<https://devfeed.tech/tags/math-verify.md>), [open-llm-leaderboard](<https://devfeed.tech/tags/open-llm-leaderboard.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [science](<https://devfeed.tech/tags/science.md>)

## AI overview

The article explains how Math-Verify was used to re-evaluate 3,751 models submitted to the Open LLM Leaderboard. It addresses answer-format, symbolic parsing, and comparison problems in the previous MATH-Hard evaluator, leading to substantially revised leaderboard results.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.