Share your thoughts, 1 month free Claude Pro on usSee more

Time-series reasoning on Sleep-CoT 1.0 (test)

69.88F1 Score

OpenTSLM SoftPrompt (Llama3.2-1B)

Updated 1mo ago

Evaluation Results

Method	Links
OpenTSLM SoftPrompt (Llama3.2-1B) 2025.10		69.88	81.08
OpenTSLM SoftPrompt (Llama3.2-3B) 2025.10		54.4	72.04
OpenTSLM Flamingo (Gemma3-270M) 2025.10		51.38	68.49
OpenTSLM Flamingo (Llama3.2-1B) 2025.10		49.33	67.31
OpenTSLM Flamingo (Llama3.2-3B) 2025.10		45.45	69.14
OpenTSLM Flamingo (Gemma3-1B-pt) 2025.10		43.69	60.67
OpenTSLM SoftPrompt (Gemma3-1B-pt) 2025.10		30.99	36.56
Gemma3-4B FT 2025.10		18.56	38.28
Random Baseline 2025.10		17.48	20
GPT-4o 2025.10		15.47	16.02
Llama3.2-1B 2025.10		9.05	24.19
OpenTSLM SoftPrompt (Gemma3-270M) 2025.10		7.96	5.91
Gemma3-4B-pt 2025.10		6.75	14.95
Llama3.2-3B 2025.10		5.86	14.3
Llama3.2-3B 2025.10		5.66	12.15
GPT-4o 2025.10		4.82	10.75
Llama3.2-1B 2025.10		2.14	0.65