List your company

Mathematical Reasoning on GSM8K (test) (Accuracy, AVG, MAX)

32AccuracyDrICL
-0.248.1316.524.87Jan 7, 2025

Evaluation results

MethodLinks
DrICLBackbone=Llama-2-7b-chat-hf, k-shot=102025.01322932
ITBackbone=Llama-2-7b-chat-hf, k-shot=02025.01312431
DrICLBackbone=Llama-2-7b-chat-hf, k-shot=32025.01312932
DrICLBackbone=Llama-2-7b-chat-hf, k-shot=02025.01302932
NFTBackbone=Llama-2-7b-chat-hf, k-shot=02025.01281128
DrICLBackbone=Llama-2-7b-chat-hf, k-shot=12025.01282932
DrICLBackbone=Llama-2-7b-chat-hf, k-shot=52025.01272932
ITBackbone=Llama-2-7b-chat-hf, k-shot=12025.01262431
ITBackbone=Llama-2-7b-chat-hf, k-shot=32025.01262431
ITBackbone=Llama-2-7b-chat-hf, k-shot=102025.01262431
MetaICLBackbone=Llama-2-7b-chat-hf, k-shot=12025.01262526
MetaICLBackbone=Llama-2-7b-chat-hf, k-shot=32025.01262526
MetaICLBackbone=Llama-2-7b-chat-hf, k-shot=202025.01262526
DrICLBackbone=Llama-2-7b-chat-hf, k-shot=202025.01262932
MetaICLBackbone=Llama-2-7b-chat-hf, k-shot=02025.01242526
MetaICLBackbone=Llama-2-7b-chat-hf, k-shot=52025.01242526
MetaICLBackbone=Llama-2-7b-chat-hf, k-shot=102025.01242526
ITBackbone=Llama-2-7b-chat-hf, k-shot=52025.01212431
NFTBackbone=Llama-2-7b-chat-hf, k-shot=12025.01161128
ITBackbone=Llama-2-7b-chat-hf, k-shot=202025.01162431
NFTBackbone=Llama-2-7b-chat-hf, k-shot=32025.01111128
NFTBackbone=Llama-2-7b-chat-hf, k-shot=52025.0171128
NFTBackbone=Llama-2-7b-chat-hf, k-shot=202025.0121128
NFTBackbone=Llama-2-7b-chat-hf, k-shot=102025.0111128