AIWARLIVE
Model matchupevidence floor: 1 labeled item per model
Side A

DeepSeek

DeepSeekholding
VS
Side B

MiniCPM

MiniCPMstrong
Head-to-head read

MiniCPM has the stronger recent editorial momentum in the labeled evidence. DeepSeek is still active on the board, but its latest reports skew less favorable.

Editorial read, not a benchmark — see /methodology.

DeepSeek Evidence
paperDeepSeek · DeepSeek
Benchmark winChina +30US -7

Pezego-HITL: A policy-grounded large language model architecture for agricultural extension in Ghana — Large language models are increasingly deployed in agricultural decision-support settings, yet high-stakes crop protection in smallholder agriculture requires more than output-q

paperDeepSeek · DeepSeek
Usage limitsChina -12

LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention — Indexer-TopK, the operation to compute the scores and select the top-k candidates, is widely used by sparse attention kernels in large language models and vector re

paperDeepSeek · DeepSeek
Usage limitsChina -12

Understanding before Naming! Enhancing LLM-based Method Name Prediction with Code Summarization — Method names are critical to software quality, affecting code comprehensibility, maintainability, and developer collaboration. However, manually designing meaningful method names is

paperDeepSeek · DeepSeek
Usage limitsChina -12

Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts — Sparse Mixture-of-Experts (MoE) models have become an important approach for scaling Large Language Models (LLMs), but their inference efficiency depends strongly on expert activation patterns

paperDeepSeek · DeepSeek
Usage limitsChina -12

LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention — Indexer-TopK, the operation to compute the scores and select the top-k candidates, is widely used by sparse attention kernels in large language models and vector re

paperDeepSeek · DeepSeek
FundingChina +18

Can Agentic Trading Systems Pay for Their Own Intelligence? — Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typicall

MiniCPM Evidence
huggingfaceMiniCPM · trending
Open weightsChina +90Open +60

GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF — Open-weight model release on Hugging Face - text-generation - 595 downloads

huggingfaceMiniCPM · trending
Open weightsChina +90Open +60

GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking — Open-weight model release on Hugging Face - text-generation - 3483 downloads

huggingfaceMiniCPM · trending
Open weightsChina +90Open +60

GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF — Open-weight model release on Hugging Face - text-generation - 2239 downloads