Knowledge-based reasoning on ECG
30.3Accuracy (%)VeriTime
Evaluation results
| Method | Links | |
|---|---|---|
| VeriTimeModel Category=Base: Qwen3-4B-Instruct, Method Variant=VeriTime (SFT+RL)2026.02 | 30.3 | |
| PatchTSTModel Category=Classical Models2026.02 | 28.39 | |
| TimesNetModel Category=Classical Models2026.02 | 28.13 | |
| DLinearModel Category=Classical Models2026.02 | 26.82 | |
| FEDformerModel Category=Classical Models2026.02 | 26.4 | |
| VeriTimeModel Category=Base: Qwen2.5-3B-Instruct, Method Variant=VeriTime (SFT+RL)2026.02 | 25.79 | |
| iTransformerModel Category=Classical Models2026.02 | 25.78 | |
| Time-MQAModel Category=Time Series Language Models, Backbone=Qwen2.5-7B2026.02 | 25 | |
| Mistral-7B-v0.3Model Category=General LLMs2026.02 | 24.74 | |
| AutoformerModel Category=Classical Models2026.02 | 23.95 | |
| Time-R1Model Category=Time Series Language Models, Backbone=Qwen2.5-7B2026.02 | 23.74 | |
| GPT-4o-miniModel Category=General LLMs2026.02 | 23.68 | |
| Qwen2.5-3B-Instruct (Base)Model Category=Base: Qwen2.5-3B-Instruct, Method Variant=Base2026.02 | 23.16 | |
| Meta-Llama3-8B-InstructModel Category=General LLMs2026.02 | 22.11 | |
| Time-MQAModel Category=Time Series Language Models, Backbone=Llama3-8B2026.02 | 21.72 | |
| DeepSeek-R1-Distill-Qwen-7BModel Category=General LLMs2026.02 | 21.58 | |
| Qwen2.5-7B-InstructModel Category=General LLMs2026.02 | 16.84 | |
| Qwen3-4B-Instruct (Base)Model Category=Base: Qwen3-4B-Instruct, Method Variant=Base2026.02 | 15.15 | |
| Time-MQAModel Category=Time Series Language Models, Backbone=Mistral-7B2026.02 | 11.62 |