Model Benchmark: First Grade Math
Performance comparison across 1,000 questions per model
Performance Overview
Models Benchmarked
FlameF0X/MathGPT2
763
Correct
237
Incorrect
FlameF0X/Muffin-2.9b-1C25
9
Correct
991
Incorrect
FlameF0X/MuffinFace-2
8
Correct
992
Incorrect