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

Linguistic Implicatures Decoding on Open PL LLM Leaderboard Implicatures Component

67.38Average Score

Qwen2.5-72B

Updated 1mo ago

Evaluation Results

Method	Links
Qwen2.5-72B 2025.12		67.38
Qwen2.5-32B 2025.12		66.73
Qwen-72B 2025.12		66.02
Qwen2.5-14B 2025.12		62.71
Meta-Llama-3-70B 2025.12		62.07
Qwen1.5-72B 2025.12		61.11
Meta-Llama-3.1-70B 2025.12		60.87
Mixtral-8x22B-v0.1 2025.12		60.75
Mistral-Small-24B-Base-2501 2025.12		59.9
Qwen1.5-32B 2025.12		58.71
Bielik-11B-v2 2025.12		58.14
Llama-4-Scout-17B-16E 2025.12		57.77
Bielik-11B-v3-Base-20250730 2025.12		55.16
Qwen2.5-7B 2025.12		53.35
EuroLLM-9B 2025.12		50.03
Qwen-7B 2025.12		49.39
SOLAR-10.7B-v1.0 2025.12		47.54
Mistral-Nemo-Base-2407 2025.12		47.28
internlm2-20b 2025.12		47.15
Bielik-4.5B-v3 2025.12		45.47
Meta-Llama-3.1-8B 2025.12		43.77
Meta-Llama-3-8B 2025.12		43.3
Qwen1.5-72B 2025.12		39.51
Mistral-7B-v0.3 2025.12		38.88
Mistral-7B-v0.2 2025.12		38.81
Qwen1.5-7B 2025.12		37.92
Bielik-7B-v0.1 2025.12		34.34
Qra-13b 2025.12		33.9
Llama-3.2-3B 2025.12		31.89
Qra-7b 2025.12		16.6