List your company

Mathematical Reasoning on GSM8K Numerical +8 (test)

67.8AccuracyCLAUDE-3-OPUS
2.90419.75236.653.448Jun 25, 2024

Evaluation results

MethodLinks
CLAUDE-3-OPUSPrompting=CoT, Framework=DARG2024.0667.8
GPT-4-OPrompting=CoT, Framework=DARG2024.0642
GPT-4-TURBOPrompting=CoT, Framework=DARG2024.0639.2
GEMINI-1.5-PROPrompting=CoT, Framework=DARG2024.0633
COMMAND R+104BPrompting=CoT, Framework=DARG2024.0632.8
GEMINI-1.5-FLASHPrompting=CoT, Framework=DARG2024.0626.4
MIXTRAL 8x22BPrompting=CoT, Framework=DARG2024.0626.2
GPT-3.5-TURBOPrompting=CoT, Framework=DARG2024.0626.2
LLAMA-3-70BPrompting=CoT, Framework=DARG2024.0621.4
DEEPSEEKMATH-7BPrompting=CoT, Framework=DARG2024.0620.4
WIZARDLM-2 8x22BPrompting=CoT, Framework=DARG2024.0618
MIXTRAL 8x7BPrompting=CoT, Framework=DARG2024.0614.4
PHI-3-MINI-3.8BPrompting=CoT, Framework=DARG2024.0613.8
LLAMA-3-8BPrompting=CoT, Framework=DARG2024.0612.8
MISTRAL-7BPrompting=CoT, Framework=DARG2024.065.4