HF Model & Benchmark Matrix

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

deepseek-ai/DeepSeek-V2-Chat

family deepseek · 1 variants · unknown

provider
deepseek-ai
released
—
huggingface
https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat
best scores
AlpacaEval: 2.0MMLU: 78.9BBH: 81.0C-Eval: 67.5CMMLU: 69.3HumanEval: 48.2MBPP: 68.6GSM8K: 83.0MATH: 42.2LiveCodeBench: 18.8

Best scores per benchmark

benchmarkcategorybest score
GSM8Kmath83.0
BBHreasoning81.0
MMLUknowledge78.9
CMMLUknowledge69.3
MBPPcoding68.6
C-Evalknowledge67.5
HumanEvalcoding48.2
MATHmath42.2
LiveCodeBenchcoding18.8
AlpacaEvalchat2.0

Variants (1)

variantkindquantbitsvRAMdlorgyear
DeepSeek-V2-Chatoriginalbf1616.010,482deepseek-ai2024
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.