Our new X account is live! Follow @wizwand_team for updates

Commonsense reasoning on PIQA 1.0 (test)

82.21Accuracy

Mistral-7B + Uniform

Updated 3d ago

Evaluation Results

Method	Links
Mistral-7B + Uniform 2024.02		82.21
Mistral-7B + AutoDS 2024.02		82.21
Mistral-7B Base 2024.02		82.1
Mistral-7B + QuRating 2024.02		81.99
Mistral-7B + DSIR 2024.02		81.94
LLaMA2-7B + Uniform 2024.02		79.54
LLaMA2-7B Base 2024.02		79.43
LLaMA2-7B + QuRating 2024.02		79
LLaMA2-7B + DSIR 2024.02		78.84
LLaMA2-7B + AutoDS 2024.02		78.18
Gemma-2B + QuRating 2024.02		77.53
Gemma-2B + AutoDS 2024.02		77.42
Gemma-2B + DSIR 2024.02		77.15
Gemma-2B + Uniform 2024.02		76.71
Gemma-2B Base 2024.02		70.67
TituLLM-3b-v2.0 2025.02		60
BLOOM-3b 2025.02		58
BLOOM-3b 2025.02		58
TituLLM-1b-v2.0 2025.02		58
TituLLM-3b-v2.0 2025.02		58
Llama-3.2-3b 2025.02		57
Llama-3.2-3b 2025.02		57
TituLLM-1b-v2.0 2025.02		57
Gemma-2-2b 2025.02		56
Gemma-2-2b 2025.02		56
BLOOM-1b7 2025.02		56
BLOOM-1b1 2025.02		55
BLOOM-1b7 2025.02		55
Llama-3.2-1b 2025.02		54
Qwen-2.5-0.5b 2025.02		54
SmolLM2-360m 2025.02		54
BLOOM-560m 2025.02		54
BLOOM-560m 2025.02		54
BLOOM-1b1 2025.02		54
Llama-3.2-1b 2025.02		53
Qwen-2.5-0.5b 2025.02		53
Qwen-2.5-1.5b 2025.02		53
SmolLM2-360m 2025.02		53
SmolLM2-1.7b 2025.02		53
SmolLM2-1.7b 2025.02		53
BongLLaMA-3.2-1b 2025.02		53
davinci 2025.02		52
Qwen-2.5-1.5b 2025.02		52
SmolLM2-135m 2025.02		52
SmolLM2-135m 2025.02		52
BongLLaMA-3.2-1b 2025.02		52
BongLLaMA-3.2-3b 2025.02		51
BongLLaMA-3.2-3b 2025.02		50