List your company

Question Answering on QA

59.5AccuracyDPS
56.17257.03657.958.764Feb 17, 2025

Evaluation results

MethodLinks
DPSLLM Backbone=Gemini-1.5 Flash2025.0259.5
DPSLLM Backbone=GPT-3.5 Turbo2025.0258.9
OPROLLM Backbone=Gemini-1.5 Flash2025.0258.9
OPROLLM Backbone=GPT-3.5 Turbo2025.0258.3
APELLM Backbone=Gemini-1.5 Flash2025.0258.1
DPSLLM Backbone=Llama-3.1 70B2025.0258.1
N/ALLM Backbone=GPT-3.5 Turbo2025.0257.8
APELLM Backbone=GPT-3.5 Turbo2025.0257.5
OPROLLM Backbone=Llama-3.1 70B2025.0257.4
APELLM Backbone=Llama-3.1 70B2025.0257.1
N/ALLM Backbone=Gemini-1.5 Flash2025.0256.9
N/ALLM Backbone=Llama-3.1 70B2025.0256.3