Question Answering on Dynamic Event Benchmark Historical
63.96Exact Match AccuracyChronosGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| ChronosGPT-4oBackbone=GPT-4o, Method Paradigm=Chronos (Ours)2026.04 | 63.96 | |
| GPT-4oBackbone=GPT-4o, Method Paradigm=Direct Generation2026.04 | 61.26 | |
| ChronosClaudeBackbone=Claude, Method Paradigm=Chronos (Ours)2026.04 | 57.66 | |
| ClaudeBackbone=Claude, Method Paradigm=Direct Generation2026.04 | 55.86 | |
| ChronosLLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Chronos (Ours)2026.04 | 50.45 | |
| WISELLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Parametric Updating Methods2026.04 | 46.85 | |
| LLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Direct Generation2026.04 | 45.95 | |
| LoRA FTLLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Parametric Updating Methods2026.04 | 35.14 | |
| Vanilla RAGClaudeBackbone=Claude, Method Paradigm=Retrieval-based Methods2026.04 | 27.03 | |
| MEMITLLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Parametric Updating Methods2026.04 | 25.23 | |
| ReAct RAGClaudeBackbone=Claude, Method Paradigm=Retrieval-based Methods2026.04 | 18.92 | |
| ROMELLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Parametric Updating Methods2026.04 | 10.81 | |
| Vanilla RAGLLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Retrieval-based Methods2026.04 | 10.81 | |
| Vanilla RAGGPT-4oBackbone=GPT-4o, Method Paradigm=Retrieval-based Methods2026.04 | 9.91 | |
| ReAct RAGGPT-4oBackbone=GPT-4o, Method Paradigm=Retrieval-based Methods2026.04 | 7.21 | |
| ReAct RAGLLaMA-3.1Backbone=LLaMA-3.1, Method Paradigm=Retrieval-based Methods2026.04 | 6.31 |