List your company
ResearchFormerly WizWand

Mathematical Reasoning on OCW-Math

26.5AccuracyGPT-4
2.3728.63614.921.164May 23, 2024
Updated 8mo ago

Evaluation results

MethodLinks
GPT-42024.0526.5
JiuZhang3.0Parameters=8x7B2024.0523.5
JiuZhang3.0Parameters=8B2024.0521.3
JiuZhang3.0Parameters=7B2024.0520.2
DeepSeekMathParameters=7B, Variant=Instruct2024.0519.5
MAmmoTH2Parameters=8x7B, Variant=Plus2024.0518.8
DeepSeekMathParameters=7B2024.0517.6
MAmmoTH2Parameters=7B, Variant=Plus2024.0515.1
MAmmoTH2Parameters=8B, Variant=Plus2024.0514.7
Qwen-1.5Parameters=110B2024.0514
LlemmaParameters=34B2024.0511.8
ChatGPT2024.0511
MixtralParameters=8x7B2024.058.8
Qwen-1.5Parameters=72B2024.057.7
LLAMA-3Parameters=8B2024.057.7
LlemmaParameters=7B2024.057.7
Intern-MathParameters=20B2024.057
Rho-1-MathParameters=7B2024.056.2
GemmaParameters=7B2024.054.8
MistralParameters=7B2024.053.3