Time-series reasoning on ECG-QA-CoT 1.0 (test)
40.25F1 ScoreOpenTSLM Flamingo (Llama3.2-3B)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OpenTSLM Flamingo (Llama3.2-3B)Category=OpenTSLM Flamingo, Base Model=Llama3.2-3B2025.10 | 40.25 | 46.25 | |
| OpenTSLM Flamingo (Gemma3-1B-pt)Category=OpenTSLM Flamingo, Base Model=Gemma3-1B-pt2025.10 | 35.31 | 37.79 | |
| OpenTSLM Flamingo (Llama3.2-1B)Category=OpenTSLM Flamingo, Base Model=Llama3.2-1B2025.10 | 34.62 | 38.14 | |
| OpenTSLM SoftPrompt (Llama3.2-3B)Category=OpenTSLM SoftPrompt, Base Model=Llama3.2-3B2025.10 | 33.67 | 36.25 | |
| OpenTSLM SoftPrompt (Llama3.2-1B)Category=OpenTSLM SoftPrompt, Base Model=Llama3.2-1B2025.10 | 32.84 | 35.49 | |
| OpenTSLM Flamingo (Gemma3-270M)Category=OpenTSLM Flamingo, Base Model=Gemma3-270M2025.10 | 32.71 | 35.5 | |
| OpenTSLM SoftPrompt (Gemma3-1B-pt)Category=OpenTSLM SoftPrompt, Base Model=Gemma3-1B-pt2025.10 | 27.86 | 34.76 | |
| Gemma3-4B FTCategory=Image (Plot), Protocol=Finetuned2025.10 | 26.17 | 38.1 | |
| GPT-4oCategory=Image (Plot), Protocol=Zero-shot2025.10 | 24.95 | 33.3 | |
| GPT-4oCategory=Tokenized Time-Series, Protocol=Zero-shot2025.10 | 18.19 | 28.76 | |
| Random BaselineCategory=Random Baseline2025.10 | 16.47 | 20.18 | |
| Gemma3-4B-ptCategory=Image (Plot), Protocol=Zero-shot2025.10 | 1.9 | 1.03 |