HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

microsoft/phi-4-reasoning

family phi · 3 variants · unknown

provider
microsoft
released
—
huggingface
https://huggingface.co/microsoft/phi-4-reasoning
best scores
OmniMath: 76.6GPQA: 65.8LiveCodeBench: 53.8IFEval: 62.3Chatbot Arena: 68.1HumanEval: 83.5MMLU-Pro: 71.5

Best scores per benchmark

benchmarkcategorybest score

Variants (3)

variantkindquantbitsvRAMdlorgyear
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.