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

Open-book Question Answering on OpenBookQA 1.0 (test)

35Accuracy

TituLLM-3b-v2.0

Updated 1mo ago

Evaluation Results

Method	Links
TituLLM-3b-v2.0 2025.02		35
Gemma-2-2b 2025.02		34
Gemma-2-2b 2025.02		33
BLOOM-3b 2025.02		33
BongLLaMA-3.2-1b 2025.02		33
TituLLM-1b-v2.0 2025.02		33
Llama-3.2-1b 2025.02		32
Llama-3.2-1b 2025.02		32
Llama-3.2-3b 2025.02		32
Llama-3.2-3b 2025.02		32
BLOOM-1b7 2025.02		32
TituLLM-1b-v2.0 2025.02		32
TituLLM-3b-v2.0 2025.02		32
Qwen-2.5-0.5b 2025.02		31
SmolLM2-135m 2025.02		31
SmolLM2-1.7b 2025.02		31
BLOOM-560m 2025.02		31
BLOOM-1b1 2025.02		31
BLOOM-1b1 2025.02		31
BLOOM-1b7 2025.02		31
BLOOM-3b 2025.02		31
BongLLaMA-3.2-1b 2025.02		31
davinci 2025.02		30
Qwen-2.5-0.5b 2025.02		30
Qwen-2.5-1.5b 2025.02		30
SmolLM2-135m 2025.02		30
SmolLM2-360m 2025.02		30
SmolLM2-1.7b 2025.02		30
Qwen-2.5-1.5b 2025.02		29
SmolLM2-360m 2025.02		29
BongLLaMA-3.2-3b 2025.02		29
BLOOM-560m 2025.02		28
BongLLaMA-3.2-3b 2025.02		27