HF Model & Benchmark Matrix

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

Home/Models/alibaba-pai/DistilQwen2.5-R1-3B

DistilQwen2.5-R1-3B

alibaba-pai/DistilQwen2.5-R1-3B

kind: original
quant: bf16 (16-bit)
family: qwen
modality: —
root model: alibaba-pai/DistilQwen2.5-R1-3B
provider: alibaba-pai
license: —
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 50
likes: 2
created: —
last modified: 2025-04-23T08:11:12+00:00 (2025)
huggingface: https://huggingface.co/alibaba-pai/DistilQwen2.5-R1-3B
tags: safetensorsqwen2region:us

Benchmark scores (4)

benchmark	category	score	context	conf	evidence
MATH-500	math	92.8		low	`\| DeepSeek-R1-Distill-Qwen-7B \| 800k \| 55.5 \| 92.8 \| 49.1 \| - \|`
AIME 2024	math	55.5		low	`\| DeepSeek-R1-Distill-Qwen-7B \| 800k \| 55.5 \| 92.8 \| 49.1 \| - \|`
GPQA Diamond	reasoning	49.1		low	`\| DeepSeek-R1-Distill-Qwen-7B \| 800k \| 55.5 \| 92.8 \| 49.1 \| - \|`
LiveCodeBench	coding	36.1		low	`\| Bespoke-Stratos-7B \| 17k \| 20.0 \| 82.0 \| 37.8 \| 36.1 \|`

Discussions (0)

none scraped.

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