HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/deepseek-ai/deepseek-ai/DeepSeek-V2.5

deepseek-ai/DeepSeek-V2.5

family deepseek · 3 variants · unknown

provider
deepseek-ai
released
—
huggingface
https://huggingface.co/deepseek-ai/DeepSeek-V2.5
best scores
AlpacaEval: 46.6Chatbot Arena: 68.3MT-Bench: 8.85HumanEval: 84.5LiveCodeBench: 36.6

Best scores per benchmark

benchmarkcategorybest score
HumanEvalcoding84.5
Chatbot Arenachat68.3
AlpacaEvalchat46.6
LiveCodeBenchcoding36.6
MT-Benchchat8.85

Variants (3)

variantkindquantbitsvRAMdlorgyear
DeepSeek-V2.5originalbf1616.04,430deepseek-ai2024
DeepSeek-V2.5-GGUFggufgguf1.0577bartowski2024
DeepSeek-V2.5-GGUFggufgguf4.0352lmstudio-community2024
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.