List your company

General Performance on AlpacaEval

98WinrateVanilla
66.874.98391.1Nov 15, 2023Feb 15, 2024May 17, 2024Aug 18, 2024Nov 18, 2024Feb 18, 2025May 22, 2025

Evaluation results

MethodLinks
VanillaModel=GPT-42023.119839
Goal PrioritizationModel=GPT-42023.119838.4
VanillaModel=ChatGPT2023.119737.8
Goal PrioritizationModel=ChatGPT2023.119636.3
Self-ReminderModel=GPT-42023.119637.4
Self-ReminderModel=ChatGPT2023.119535.2
VanillaModel=Vicuna-33B2023.119536.6
Goal PrioritizationModel=Vicuna-33B2023.119233.8
VanillaModel=Llama2-13B-Chat2023.119133.8
VanillaModel=Llama2-7B-Chat2023.118834.9
Self-ReminderModel=Vicuna-33B2023.118633.3
VanillaModel=Vicuna-13B2023.118432.6
Goal PrioritizationModel=Vicuna-13B2023.118431.1
Goal PrioritizationModel=Llama2-13B-Chat2023.118129.6
BaselineTarget Model=Zephyr-7B-Beta2025.0578.35—
VanillaModel=Vicuna-7B2023.117830.9
MTSA-T3Target Model=Zephyr-7B-Beta, Iteration=32025.0577.45—
Self-ReminderModel=Vicuna-13B2023.117629.3
Self-ReminderModel=Llama2-7B-Chat2023.117529.8
Goal PrioritizationModel=Llama2-7B-Chat2023.117428.8
Self-ReminderModel=Llama2-13B-Chat2023.117429.9
Self-ReminderModel=Vicuna-7B2023.117229.1
BaselineTarget Model=Llama2-7B-Chat2025.0571.39—
MTSA-T3Target Model=Llama2-7B-Chat, Iteration=32025.0570.21—
Goal PrioritizationModel=Vicuna-7B2023.116827.5