List your company
ResearchFormerly WizWand

Temporal Question Answering on TransientTables (test)

80.39EMGemini-2.0-Flash
27.807641.458855.1168.7612Nov 29, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Gemini-2.0-FlashSchema Generator=Gemini 2.5 Flash, Approach=Evidence-Guided Schema Normalization2025.1180.3982.11
Llama-3.3-70B-InstructSchema Generator=Llama-3.3-70B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1179.5279.91
Llama-3.1-8B-InstructSchema Generator=Llama-3.3-70B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1178.777.85
GPT-4o-miniSchema Generator=Llama-3.3-70B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1178.5478.7
Gemini-2.5-ProSchema Generator=Llama-3.3-70B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1178.5178.2
Llama-3.1-8B-InstructSchema Generator=Gemini 2.5 Flash, Approach=Evidence-Guided Schema Normalization2025.1178.0879.49
Qwen2.5-7B-InstructSchema Generator=Gemini 2.5 Flash, Approach=Evidence-Guided Schema Normalization2025.1177.8478.86
Qwen2.5-7B-InstructSchema Generator=Llama-3.3-70B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1175.375.07
Gemini-2.0-FlashSchema Generator=Llama-3.3-70B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1172.773.33
Llama-3.3-70B-InstructSchema Generator=Gemini 2.5 Flash, Approach=Evidence-Guided Schema Normalization2025.1169.8675.54
GPT-4o-miniSchema Generator=Gemini 2.5 Flash, Approach=Evidence-Guided Schema Normalization2025.1169.5666.8
Gemini-2.5-ProSchema Generator=IRE+CoT, Approach=Baseline2025.1168.8975.3
Gemini-2.5-ProSchema Generator=Gemini 2.5 Flash, Approach=Evidence-Guided Schema Normalization2025.1168.2567.18
Llama-3.3-70B-InstructSchema Generator=Llama-3.1-8B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1164.7963.66
Gemini-2.5-ProSchema Generator=Llama-3.1-8B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1163.1363.07
GPT-4o-miniSchema Generator=Llama-3.1-8B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1162.8863.15
Llama-3.1-8B-InstructSchema Generator=Llama-3.1-8B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1161.7860.66
Qwen2.5-7B-InstructSchema Generator=Llama-3.1-8B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1160.9160.32
Gemini-2.0-FlashSchema Generator=Llama-3.1-8B-Instruct, Approach=Evidence-Guided Schema Normalization2025.1160.3760.32
Gemini-2.0-FlashSchema Generator=IRE+CoT, Approach=Baseline2025.1148.9855.93
GPT-4o-miniSchema Generator=IRE+CoT, Approach=Baseline2025.1144.5352.27
Llama-3.3-70B-InstructSchema Generator=IRE+CoT, Approach=Baseline2025.1141.0854.91
Qwen2.5-7B-InstructSchema Generator=IRE+CoT, Approach=Baseline2025.1130.429.22
Llama-3.1-8B-InstructSchema Generator=IRE+CoT, Approach=Baseline2025.1129.8337.95