HF Model & Benchmark Matrix

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

DeepSeek-R1-Zero

deepseek-ai/DeepSeek-R1-Zero

kind
fp8
quant
fp8 (8-bit)
family
deepseek
modality
text-generation
root model
deepseek-ai/DeepSeek-R1-Zero
provider
deepseek-ai
license
mit
language
—
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
5,179
likes
959
created
—
last modified
2025-03-27T04:02:04+00:00 (2025)
huggingface
https://huggingface.co/deepseek-ai/DeepSeek-R1-Zero
tags
transformerssafetensorsdeepseek_v3text-generationconversationalcustom_codearxiv:2501.12948license:mittext-generation-inferenceendpoints_compatiblefp8region:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
MATH-500math74.6low| GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 |
GPQA Diamondreasoning49.9low| GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 |
LiveCodeBenchcoding32.9low| GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 |
MATHmath16.0Mathmedium| Math | AIME 2024 (Pass@1) | 16.0 | 9.3 | 39.2 | 63.6 | 79.2 | **79.8** |
AIME 2024math9.3low| GPT-4o-0513 | 9.3 | 13.4 | 74.6 | 49.9 | 32.9 | 759 |

Discussions (0)

none scraped.

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