Mathematical Reasoning
Solving math word problems (GSM8K, MATH, Minerva).
Benchmarks & Datasets
GSM8K
8,500 grade school math word problems requiring multi-step reasoning. The most popular math reasoning benchmark.
N/A
Images
2021
Year
See Leaderboard
MATH
12,500 competition mathematics problems from AMC, AIME, and other sources. Harder than GSM8K.
N/A
Images
2021
Year
See Leaderboard
AIME 2024
30 challenging math problems from the 2024 AIME competition. Tests advanced mathematical reasoning.
N/A
Images
2024
Year
See Leaderboard