Motif Classification on LLMTM 1.0 (test) benchmark leaderboard · SOTA2 Research

Motif Classification on LLMTM 1.0 (test)

1003-starDeepSeek-R1-Distill-Qwen-14B

Evaluation Results

Method	Links
DeepSeek-R1-Distill-Qwen-14B2025.12		100	90	95	100	90	100	100	100	90
Qwen2.5-32B-Instruct2025.12		100	80	90	90	95	90	75	70	90
QwQ-32B2025.12		100	95	95	90	100	90	95	90	85
GPT-4o-mini2025.12		100	90	100	90	95	90	90	85	85
DeepSeek-R12025.12		100	95	100	95	90	100	100	100	100
o32025.12		100	100	100	100	95	90	90	100	100
DeepSeek-R1-Distill-Qwen-32B2025.12		95	95	95	90	95	100	100	100	85
DeepSeek-Qwen-7B2025.12		90	95	95	65	65	90	45	80	90
DeepSeek-Qwen-7B2025.12		60	50	65	50	65	60	35	50	55
openPangu-7B2025.12		55	60	70	70	55	75	65	70	60
DeepSeek-Qwen-7B2025.12		50	50	65	50	65	60	65	65	50
DeepSeek-Qwen-7B2025.12		50	50	65	50	65	60	65	65	50