HF Model & Benchmark Matrix

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

rho-math-7b-v0.1

microsoft/rho-math-7b-v0.1

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
microsoft/rho-math-7b-v0.1
provider
microsoft
license
mit
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
54
likes
20
created
—
last modified
2025-12-17T18:22:55+00:00 (2025)
huggingface
https://huggingface.co/microsoft/rho-math-7b-v0.1
tags
transformerssafetensorsmistraltext-generationnlpmathenarxiv:2404.07965license:mittext-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (8)

benchmarkcategoryscorecontextconfevidence
MATHmath81.3[Rho-Math-7B-Interpreter-v0.1](https://huggingface.co/microsoft/rho--7b-interpreter-v0.1)medium| [Rho-Math-7B-Interpreter-v0.1](https://huggingface.co/microsoft/rho-math-7b-interpreter-v0.1) | 7B | ToRA-69k | 81.3 | **51.8** | 80.8 | 85.5 | **94.5** | 70.1 | 63.1 | 75.3 |
MATHmath66.9[Rho-Math-7B-v0.1](https://huggingface.co/microsoft/rho--7b-v0.1)medium| [Rho-Math-7B-v0.1](https://huggingface.co/microsoft/rho-math-7b-v0.1) | 7B | OWM | 14B | 10.5B | **66.9** | 31.0 | 54.6 | **84.4** |
MATHmath65.4InternLM2-Mathmedium| InternLM2-Math | 20B | - | 31B | 125B | 65.4 | 30.0 | 53.1 | 71.9 |
MATHmath59.4[Rho-Math-1B-Interpreter-v0.1](https://huggingface.co/microsoft/rho--1b-interpreter-v0.1)medium| [Rho-Math-1B-Interpreter-v0.1](https://huggingface.co/microsoft/rho-math-1b-interpreter-v0.1) | 1B | ToRA-69k | 59.4 | 40.6 | 60.7 | 74.2 | 88.6 | 26.7 | 48.1 | 56.9 |
MATHmath36.2[Rho-Math-1B-v0.1](https://huggingface.co/microsoft/rho--1b-v0.1)medium| [Rho-Math-1B-v0.1](https://huggingface.co/microsoft/rho-math-1b-v0.1) | 1.1B | OWM | 14B | 30B | **36.2** | **15.6** | 23.3 | 28.1 |
GSM8Kmath36.1low| Qwen1.5 | 1.8B | - | - | - | 36.1 | 6.8 | 31.3 | 40.6 |
MMLUknowledge31.3low| Qwen1.5 | 1.8B | - | - | - | 36.1 | 6.8 | 31.3 | 40.6 |
MATHmath6.8low| Qwen1.5 | 1.8B | - | - | - | 36.1 | 6.8 | 31.3 | 40.6 |

Discussions (0)

none scraped.

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