← Back

MATH-500

other 1 mention from 1 sources

A mathematical reasoning benchmark dataset used to evaluate AI model performance on solving math problems.

evaluation math dataset benchmark
1

sources

Mentioned by

Sebastian Raschka

All mentions

Sebastian Raschka uses this ✓ High confidence
"I was training the Qwen 3 base model with RLVR on MATH-500. The base model had an accuracy of about 15%."
From: State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490 • ▶ 1:44:20 • Jan 2026

Attribution: Sebastian mentions using MATH-500 as a benchmark for training and evaluating the Qwen 3 model