HF Model & Benchmark Matrix

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

Phi-4-reasoning-vision-15B

microsoft/Phi-4-reasoning-vision-15B

kind
original
quant
bf16 (16-bit)
family
phi
modality
image-text-to-text
root model
microsoft/Phi-4-reasoning
provider
microsoft
license
mit
language
en
context
16,384
library
—
vRAM (GB)
—
size on disk
—
downloads
6,315
likes
175
created
—
last modified
2026-03-18T16:38:24+00:00 (2026)
huggingface
https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B
tags
safetensorsphi4-siglipmultimodalvision-languagereasoningmathocrgui-groundingcomputer-usechain-of-thoughtimage-text-to-textconversationalcustom_codeenbase_model:microsoft/Phi-4-reasoningbase_model:finetune:microsoft/Phi-4-reasoninglicense:mitmodel-indexregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
ChartQAmultimodal83.3ChartQA_TESTmedium| ChartQA_TEST | 83.3 | 76.5 | 23.5 | 87 | 39 | 83.1 | 83.2 | 84.3 | 84 |
MathVistamultimodal75.2MathVista_MINImedium| MathVista_MINI | 75.2 | 68.7 | 50.5 | 67.1 | 57.4 | 77.1 | 76.4 | 82.5 | 81.8 |

Discussions (0)

none scraped.

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